public void LearningInLayerTest(int width, int height, string imageName)
{
// Prepare test output folder
var outFolder = EnsureFolderExist(nameof(ImageEncoderTest));
// Prepare input file for test
string inputImage = Path.Combine("TestFiles", imageName);
// Initialize Image Encoder
ImageEncoder encoder = new ImageEncoder(new BinarizerParams {
ImageWidth = width, ImageHeight = height
});
// Initialize HTMModules
int inputBits = width * height;
int numColumns = 1024;
HtmConfig cfg = new HtmConfig(new int[] { inputBits }, new int[] { numColumns });
var mem = new Connections(cfg);
SpatialPoolerMT sp = new SpatialPoolerMT();
sp.Init(mem);
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp);
//Test Compute method
var computeResult = layer1.Compute(inputImage, true) as int[];
var activeCellList = GetActiveCells(computeResult);
Debug.WriteLine($"Active Cells computed from Image {inputImage}: {activeCellList}");
}
private void RunSpStabilityExperiment_1(int inputBits, Parameters p, EncoderBase encoder, List <double> inputValues)
{
string path = nameof(SpatialPooler_Stability_Experiment_1);
if (Directory.Exists(path))
{
Directory.Delete(path, true);
}
while (true)
{
Directory.CreateDirectory(path);
if (Directory.Exists(path) == false)
{
Thread.Sleep(300);
}
else
{
break;
}
}
Stopwatch sw = new Stopwatch();
sw.Start();
bool learn = true;
CortexNetwork net = new CortexNetwork("my cortex");
List <CortexRegion> regions = new List <CortexRegion>();
CortexRegion region0 = new CortexRegion("1st Region");
regions.Add(region0);
SpatialPooler sp1 = new SpatialPooler();
var mem = new Connections();
p.apply(mem);
sp1.Init(mem, UnitTestHelpers.GetMemory());
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
//
// NewBorn learning stage.
region0.AddLayer(layer1);
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp1);
HtmClassifier <double, ComputeCycle> cls = new HtmClassifier <double, ComputeCycle>();
double[] inputs = inputValues.ToArray();
int[] prevActiveCols = new int[0];
int maxSPLearningCycles = 10000;
List <(double Element, (int Cycle, double Similarity)[] Oscilations)> oscilationResult = new List <(double Element, (int Cycle, double Similarity)[] Oscilations)>();
private static void Inference(int input, bool learn, CortexLayer <object, object> layer1, HtmClassifier <string, ComputeCycle> cls)
{
var result = layer1.Compute(input, false) as ComputeCycle;
var predresult = cls.GetPredictedInputValues(result.PredictiveCells.ToArray(), 3);
Console.WriteLine("\n The predictions are:");
foreach (var ans in predresult)
{
Console.WriteLine($"Predicted Input: {string.Join(", ", ans.PredictedInput)}," +
$"\tSimilarity Percentage: {string.Join(", ", ans.Similarity)}, " +
$"\tNumber of Same Bits: {string.Join(", ", ans.NumOfSameBits)}");
}
}
/// <summary>
///
/// </summary>
private void RunExperiment(int inputBits, Parameters p, EncoderBase encoder, List <double> inputValues)
{
Stopwatch sw = new Stopwatch();
sw.Start();
//INeuroVisualizer vis = new WSNeuroVisualizer();
//vis.InitModelAsync(new NeuroModel(null, (new long [10, 0]), 6));
int maxMatchCnt = 0;
bool learn = true;
//INeuroVisualizer vis = new WSNeuroVisualizer();
//GenerateNeuroModel model = new GenerateNeuroModel();
//vis.InitModel(model.CreateNeuroModel(new int[] { 1}, (long[,])p[KEY.COLUMN_DIMENSIONS], (int)p[KEY.CELLS_PER_COLUMN]));
CortexNetwork net = new CortexNetwork("my cortex");
List <CortexRegion> regions = new List <CortexRegion>();
CortexRegion region0 = new CortexRegion("1st Region");
regions.Add(region0);
SpatialPoolerMT sp1 = new SpatialPoolerMT();
TemporalMemory tm1 = new TemporalMemory();
var mem = new Connections();
p.apply(mem);
sp1.init(mem, UnitTestHelpers.GetMemory());
tm1.init(mem);
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
//
// NewBorn learning stage.
region0.AddLayer(layer1);
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp1);
HtmClassifier <double, ComputeCycle> cls = new HtmClassifier <double, ComputeCycle>();
double[] inputs = inputValues.ToArray();
int[] prevActiveCols = new int[0];
int maxSPLearningCycles = 5;
List <(double Element, (int Cycle, double Similarity)[] Oscilations)> oscilationResult = new List <(double Element, (int Cycle, double Similarity)[] Oscilations)>();
/// <summary>
///
/// </summary>
private void RunSpStabilityExperiment(int inputBits, Parameters p, EncoderBase encoder, List <double> inputValues)
{
Stopwatch sw = new Stopwatch();
sw.Start();
bool learn = true;
CortexNetwork net = new CortexNetwork("my cortex");
List <CortexRegion> regions = new List <CortexRegion>();
CortexRegion region0 = new CortexRegion("1st Region");
regions.Add(region0);
SpatialPooler sp1 = new SpatialPooler();
var mem = new Connections();
p.apply(mem);
sp1.Init(mem, UnitTestHelpers.GetMemory());
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
//
// NewBorn learning stage.
region0.AddLayer(layer1);
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp1);
HtmClassifier <double, ComputeCycle> cls = new HtmClassifier <double, ComputeCycle>();
double[] inputs = inputValues.ToArray();
int[] prevActiveCols = new int[0];
int maxSPLearningCycles = 25000;
List <(double Element, (int Cycle, double Similarity)[] Oscilations)> oscilationResult = new List <(double Element, (int Cycle, double Similarity)[] Oscilations)>();
/// <summary>
///
/// </summary>
private void RunExperiment(int inputBits, Parameters p, EncoderBase encoder, List <double> inputValues)
{
Stopwatch sw = new Stopwatch();
sw.Start();
int maxMatchCnt = 0;
bool learn = true;
CortexNetwork net = new CortexNetwork("my cortex");
List <CortexRegion> regions = new List <CortexRegion>();
CortexRegion region0 = new CortexRegion("1st Region");
regions.Add(region0);
var mem = new Connections();
p.apply(mem);
//bool isInStableState = false;
//HtmClassifier<double, ComputeCycle> cls = new HtmClassifier<double, ComputeCycle>();
HtmClassifier <string, ComputeCycle> cls = new HtmClassifier <string, ComputeCycle>();
var numInputs = inputValues.Distinct().ToList().Count;
TemporalMemory tm1 = new TemporalMemory();
HomeostaticPlasticityController hpa = new HomeostaticPlasticityController(mem, numInputs * 55, (isStable, numPatterns, actColAvg, seenInputs) =>
{
if (isStable)
{
// Event should be fired when entering the stable state.
Debug.WriteLine($"STABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
else
{
// Ideal SP should never enter unstable state after stable state.
Debug.WriteLine($"INSTABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
Assert.IsTrue(numPatterns == numInputs);
//isInStableState = true;
cls.ClearState();
tm1.Reset(mem);
}, numOfCyclesToWaitOnChange: 25);
SpatialPoolerMT sp1 = new SpatialPoolerMT(hpa);
sp1.Init(mem, UnitTestHelpers.GetMemory());
tm1.Init(mem);
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
region0.AddLayer(layer1);
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp1);
layer1.HtmModules.Add("tm", tm1);
double[] inputs = inputValues.ToArray();
int[] prevActiveCols = new int[0];
int cycle = 0;
int matches = 0;
string lastPredictedValue = "0";
Dictionary <double, List <List <int> > > activeColumnsLst = new Dictionary <double, List <List <int> > >();
foreach (var input in inputs)
{
if (activeColumnsLst.ContainsKey(input) == false)
{
activeColumnsLst.Add(input, new List <List <int> >());
}
}
int maxCycles = 3500;
int maxPrevInputs = inputValues.Count - 1;
List <string> previousInputs = new List <string>();
previousInputs.Add("-1.0");
//
// Now training with SP+TM. SP is pretrained on the given input pattern.
for (int i = 0; i < maxCycles; i++)
{
matches = 0;
cycle++;
Debug.WriteLine($"-------------- Cycle {cycle} ---------------");
foreach (var input in inputs)
{
Debug.WriteLine($"-------------- {input} ---------------");
var lyrOut = layer1.Compute(input, learn) as ComputeCycle;
var activeColumns = layer1.GetResult("sp") as int[];
activeColumnsLst[input].Add(activeColumns.ToList());
previousInputs.Add(input.ToString());
if (previousInputs.Count > maxPrevInputs + 1)
{
previousInputs.RemoveAt(0);
}
string key = GetKey(previousInputs, input);
List <Cell> actCells;
if (lyrOut.ActiveCells.Count == lyrOut.WinnerCells.Count)
{
actCells = lyrOut.ActiveCells;
}
else
{
actCells = lyrOut.WinnerCells;
}
cls.Learn(key, actCells.ToArray());
if (learn == false)
{
Debug.WriteLine($"Inference mode");
}
Debug.WriteLine($"Col SDR: {Helpers.StringifyVector(lyrOut.ActivColumnIndicies)}");
Debug.WriteLine($"Cell SDR: {Helpers.StringifyVector(actCells.Select(c => c.Index).ToArray())}");
if (key == lastPredictedValue)
{
matches++;
Debug.WriteLine($"Match. Actual value: {key} - Predicted value: {lastPredictedValue}");
}
else
{
Debug.WriteLine($"Missmatch! Actual value: {key} - Predicted value: {lastPredictedValue}");
}
if (lyrOut.PredictiveCells.Count > 0)
{
var predictedInputValue = cls.GetPredictedInputValue(lyrOut.PredictiveCells.ToArray());
Debug.WriteLine($"Current Input: {input} \t| Predicted Input: {predictedInputValue}");
lastPredictedValue = predictedInputValue;
}
else
{
Debug.WriteLine($"NO CELLS PREDICTED for next cycle.");
lastPredictedValue = string.Empty;
}
}
// The brain does not do that this way, so we don't use it.
// tm1.reset(mem);
double accuracy = matches / (double)inputs.Length * 100.0;
Debug.WriteLine($"Cycle: {cycle}\tMatches={matches} of {inputs.Length}\t {accuracy}%");
if (accuracy == 100.0)
{
maxMatchCnt++;
Debug.WriteLine($"100% accuracy reched {maxMatchCnt} times.");
if (maxMatchCnt >= 30)
{
sw.Stop();
Debug.WriteLine($"Exit experiment in the stable state after 30 repeats with 100% of accuracy. Elapsed time: {sw.ElapsedMilliseconds / 1000 / 60} min.");
learn = false;
//var testInputs = new double[] { 0.0, 2.0, 3.0, 4.0, 5.0, 6.0, 5.0, 4.0, 3.0, 7.0, 1.0, 9.0, 12.0, 11.0, 0.0, 1.0 };
// C-0, D-1, E-2, F-3, G-4, H-5
//var testInputs = new double[] { 0.0, 0.0, 4.0, 4.0, 5.0, 5.0, 4.0, 3.0, 3.0, 2.0, 2.0, 1.0, 1.0, 0.0 };
//// Traverse the sequence and check prediction.
//foreach (var input in inputValues)
//{
// var lyrOut = layer1.Compute(input, learn) as ComputeCycle;
// predictedInputValue = cls.GetPredictedInputValue(lyrOut.predictiveCells.ToArray());
// Debug.WriteLine($"I={input} - P={predictedInputValue}");
//}
/*
* //
* // Here we let the HTM predict sequence five times on its own.
* // We start with last predicted value.
* int cnt = 5 * inputValues.Count;
*
* Debug.WriteLine("---- Start Predicting the Sequence -----");
*
* //
* // This code snippet starts with some input value and tries to predict all next inputs
* // as they have been learned as a sequence.
* // We take a random value to start somwhere in the sequence.
* var predictedInputValue = inputValues[new Random().Next(0, inputValues.Count - 1)].ToString();
*
* List<string> predictedValues = new List<string>();
*
* while (--cnt > 0)
* {
* //var lyrOut = layer1.Compute(predictedInputValue, learn) as ComputeCycle;
* var lyrOut = layer1.Compute(double.Parse(predictedInputValue[predictedInputValue.Length - 1].ToString()), false) as ComputeCycle;
* predictedInputValue = cls.GetPredictedInputValue(lyrOut.PredictiveCells.ToArray());
* predictedValues.Add(predictedInputValue);
* };
*
* // Now we have a sequence of elements and watch in the trace if it matches to defined input set.
* foreach (var item in predictedValues)
* {
* Debug.Write(item);
* Debug.Write(" ,");
* }*/
break;
}
}
else if (maxMatchCnt > 0)
{
Debug.WriteLine($"At 100% accuracy after {maxMatchCnt} repeats we get a drop of accuracy with {accuracy}. This indicates instable state. Learning will be continued.");
maxMatchCnt = 0;
}
}
Debug.WriteLine("---- cell state trace ----");
cls.TraceState($"cellState_MinPctOverlDuty-{p[KEY.MIN_PCT_OVERLAP_DUTY_CYCLES]}_MaxBoost-{p[KEY.MAX_BOOST]}.csv");
Debug.WriteLine("---- Spatial Pooler column state ----");
foreach (var input in activeColumnsLst)
{
using (StreamWriter colSw = new StreamWriter($"ColumState_MinPctOverlDuty-{p[KEY.MIN_PCT_OVERLAP_DUTY_CYCLES]}_MaxBoost-{p[KEY.MAX_BOOST]}_input-{input.Key}.csv"))
{
Debug.WriteLine($"------------ {input.Key} ------------");
foreach (var actCols in input.Value)
{
Debug.WriteLine(Helpers.StringifyVector(actCols.ToArray()));
colSw.WriteLine(Helpers.StringifyVector(actCols.ToArray()));
}
}
}
Debug.WriteLine("------------ END ------------");
}
public void InputBitsExperiment(int W, int InputB, int loop)
{
string filename = "InputBits" + InputB + ".csv";
using (StreamWriter writer = new StreamWriter(filename))
{
Debug.WriteLine($"Learning Cycles: {460}");
Debug.WriteLine("Cycle;Similarity");
//Parent Loop
for (int j = 0; j < loop; j++)
{
int inputBits = InputB;
bool learn = true;
Parameters p = Parameters.getAllDefaultParameters();
p.Set(KEY.RANDOM, new ThreadSafeRandom(42));
p.Set(KEY.INPUT_DIMENSIONS, new int[] { inputBits });
p.Set(KEY.CELLS_PER_COLUMN, 5);
p.Set(KEY.COLUMN_DIMENSIONS, new int[] { 500 });
CortexNetwork net = new CortexNetwork("my cortex");
List <CortexRegion> regions = new List <CortexRegion>();
CortexRegion region0 = new CortexRegion("1st Region");
regions.Add(region0);
SpatialPoolerMT sp1 = new SpatialPoolerMT();
TemporalMemory tm1 = new TemporalMemory();
var mem = new Connections();
p.apply(mem);
sp1.Init(mem, UnitTestHelpers.GetMemory());
tm1.Init(mem);
Dictionary <string, object> settings = new Dictionary <string, object>()
{
{ "W", W },
{ "N", inputBits },
{ "Radius", -1.0 },
{ "MinVal", 0.0 },
// { "MaxVal", 20.0 },
{ "Periodic", false },
{ "Name", "scalar" },
{ "ClipInput", false },
};
double max = 10;
List <double> lst = new List <double>();
for (double i = max - 1; i >= 0; i--)
{
lst.Add(i);
}
settings["MaxVal"] = max;
EncoderBase encoder = new ScalarEncoder(settings);
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
//
// NewBorn learning stage.
region0.AddLayer(layer1);
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp1);
HtmClassifier <double, ComputeCycle> cls = new HtmClassifier <double, ComputeCycle>();
double[] inputs = lst.ToArray();
//
// This trains SP.
foreach (var input in inputs)
{
Debug.WriteLine($" ** {input} **");
for (int i = 0; i < 3; i++)
{
var lyrOut = layer1.Compute(input, learn) as ComputeCycle;
}
}
// Here we add TM module to the layer.
layer1.HtmModules.Add("tm", tm1);
int cycle = 0;
int matches = 0;
double lastPredictedValue = 0;
//
// Now, training with SP+TM. SP is pretrained on pattern.
//Child loop
for (int i = 0; i < 460; i++)
{
matches = 0;
cycle++;
foreach (var input in inputs)
{
var lyrOut = layer1.Compute(input, learn) as ComputeCycle;
cls.Learn(input, lyrOut.ActiveCells.ToArray(), lyrOut.PredictiveCells.ToArray());
Debug.WriteLine($"-------------- {input} ---------------");
if (learn == false)
{
Debug.WriteLine($"Inference mode");
}
Debug.WriteLine($"W: {Helpers.StringifyVector(lyrOut.WinnerCells.Select(c => c.Index).ToArray())}");
Debug.WriteLine($"P: {Helpers.StringifyVector(lyrOut.PredictiveCells.Select(c => c.Index).ToArray())}");
var predictedValue = cls.GetPredictedInputValue(lyrOut.PredictiveCells.ToArray());
Debug.WriteLine($"Current Input: {input} \t| - Predicted value in previous cycle: {lastPredictedValue} \t| Predicted Input for the next cycle: {predictedValue}");
if (input == lastPredictedValue)
{
matches++;
Debug.WriteLine($"Match {input}");
}
else
{
Debug.WriteLine($"Missmatch Actual value: {input} - Predicted value: {lastPredictedValue}");
}
lastPredictedValue = predictedValue;
}
if (i == 500)
{
Debug.WriteLine("Stop Learning From Here. Entering inference mode.");
learn = false;
}
//tm1.reset(mem);
Debug.WriteLine($"Cycle: {cycle}\tMatches={matches} of {inputs.Length}\t {matches / (double)inputs.Length * 100.0}%");
if (matches / (double)inputs.Length == 1)
{
writer.WriteLine($"{cycle}");
break;
}
}
}
Debug.WriteLine("New Iteration");
}
//cls.TraceState();
Debug.WriteLine("------------------------------------------------------------------------\n----------------------------------------------------------------------------");
}
private void RunSerializationExperiment(double maxBoost, double minOverlapCycles, int inputBits, Parameters p, EncoderBase encoder, List <double> inputValues)
{
string path = nameof(RunSerializationExperiment);
if (Directory.Exists(path))
{
Directory.Delete(path, true);
}
Directory.CreateDirectory(path);
Stopwatch sw = new Stopwatch();
sw.Start();
bool learn = true;
CortexNetwork net = new CortexNetwork("my cortex");
List <CortexRegion> regions = new List <CortexRegion>();
CortexRegion region0 = new CortexRegion("1st Region");
regions.Add(region0);
var mem = new Connections();
bool isInStableState = false;
HomeostaticPlasticityController hpa = new HomeostaticPlasticityController(mem, inputValues.Count * 15, (isStable, numPatterns, actColAvg, seenInputs) =>
{
Assert.IsTrue(numPatterns == inputValues.Count);
// Event should only be fired when entering the stable state.
// Ideal SP should never enter unstable state after stable state.
if (isStable == false)
{
isInStableState = false;
Debug.WriteLine($"UNSTABLE!: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
else
{
//Assert.IsTrue(isStable);
isInStableState = true;
Debug.WriteLine($"STABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
});
SpatialPooler sp1 = new SpatialPooler(hpa);
p.apply(mem);
sp1.Init(mem, UnitTestHelpers.GetMemory());
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
region0.AddLayer(layer1);
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp1);
HtmClassifier <double, ComputeCycle> cls = new HtmClassifier <double, ComputeCycle>();
double[] inputs = inputValues.ToArray();
Dictionary <double, int[]> prevActiveCols = new Dictionary <double, int[]>();
Dictionary <double, double> prevSimilarity = new Dictionary <double, double>();
foreach (var input in inputs)
{
prevSimilarity.Add(input, 0.0);
prevActiveCols.Add(input, new int[0]);
}
int maxSPLearningCycles = 5000;
List <(double Element, (int Cycle, double Similarity)[] Oscilations)> oscilationResult = new List <(double Element, (int Cycle, double Similarity)[] Oscilations)>();
/// <summary>
///
/// </summary>
private async Task RunExperimentNeuroVisualizer(int inputBits, Parameters p, EncoderBase encoder, List <double> inputValues)
{
Stopwatch sw = new Stopwatch();
sw.Start();
int maxMatchCnt = 0;
bool learn = true;
INeuroVisualizer vis = new WSNeuroVisualizer();
GenerateNeuroModel model = new GenerateNeuroModel();
await vis.ConnectToWSServerAsync();
await vis.InitModelAsync(model.CreateNeuroModel(new int[] { 1 }, (long[, ])p[KEY.COLUMN_DIMENSIONS], (int)p[KEY.CELLS_PER_COLUMN]));
CortexNetwork net = new CortexNetwork("my cortex");
List <CortexRegion> regions = new List <CortexRegion>();
CortexRegion region0 = new CortexRegion("1st Region");
regions.Add(region0);
SpatialPoolerMT sp1 = new SpatialPoolerMT();
TemporalMemory tm1 = new TemporalMemory();
var mem = new Connections();
p.apply(mem);
sp1.Init(mem, UnitTestHelpers.GetMemory());
tm1.Init(mem);
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
//
// NewBorn learning stage.
region0.AddLayer(layer1);
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp1);
//HtmClassifier<double, ComputeCycle> cls = new HtmClassifier<double, ComputeCycle>();
HtmClassifier <string, ComputeCycle> cls = new HtmClassifier <string, ComputeCycle>();
double[] inputs = inputValues.ToArray();
int[] prevActiveCols = new int[0];
int maxSPLearningCycles = 50;
//
// This trains SP on input pattern.
// It performs some kind of unsupervised new-born learning.
foreach (var input in inputs)
{
List <(int Cycle, double Similarity)> elementOscilationResult = new List <(int Cycle, double Similarity)>();
Debug.WriteLine($"Learning ** {input} **");
for (int i = 0; i < maxSPLearningCycles; i++)
{
var lyrOut = layer1.Compute((object)input, learn) as ComputeCycle;
var activeColumns = layer1.GetResult("sp") as int[];
var actCols = activeColumns.OrderBy(c => c).ToArray();
var similarity = MathHelpers.CalcArraySimilarity(prevActiveCols, actCols);
await vis.UpdateColumnAsync(GetColumns(actCols));
Debug.WriteLine($" {i.ToString("D4")} SP-OUT: [{actCols.Length}/{similarity.ToString("0.##")}] - {Helpers.StringifyVector(actCols)}");
prevActiveCols = activeColumns;
}
}
// Here we add TM module to the layer.
layer1.HtmModules.Add("tm", tm1);
int cycle = 0;
int matches = 0;
string lastPredictedValue = "0";
Dictionary <double, List <List <int> > > activeColumnsLst = new Dictionary <double, List <List <int> > >();
foreach (var input in inputs)
{
if (activeColumnsLst.ContainsKey(input) == false)
{
activeColumnsLst.Add(input, new List <List <int> >());
}
}
int maxCycles = 3500;
//
// Now training with SP+TM. SP is pretrained on the given input pattern.
for (int i = 0; i < maxCycles; i++)
{
matches = 0;
cycle++;
Debug.WriteLine($"-------------- Cycle {cycle} ---------------");
string prevInput = "-1.0";
//
// Activate the 'New - Born' effect.
//if (i == 300)
//{
// mem.setMaxBoost(0.0);
// mem.updateMinPctOverlapDutyCycles(0.0);
// cls.ClearState();
//}
foreach (var input in inputs)
{
Debug.WriteLine($"-------------- {input} ---------------");
var lyrOut = layer1.Compute(input, learn) as ComputeCycle;
var activeColumns = layer1.GetResult("sp") as int[];
activeColumnsLst[input].Add(activeColumns.ToList());
//cls.Learn(input, lyrOut.ActiveCells.ToArray());
cls.Learn(GetKey(prevInput, input), lyrOut.ActiveCells.ToArray());
List <Synapse> synapses = new List <Synapse>();
Cell cell = new Cell(0, 1, 6, 0, CellActivity.ActiveCell); // where to get all these values
Synapse synap = new Synapse(cell, 1, 1, 0.78); // here is just supposed to update the permanence, all other values remains same; where do we get all other values
synapses.Add(synap);
await vis.UpdateSynapsesAsync(synapses); //update Synapse or add new ones
await vis.UpdateCellsAsync(GetCells(lyrOut.ActiveCells));
if (learn == false)
{
Debug.WriteLine($"Inference mode");
}
if (GetKey(prevInput, input) == lastPredictedValue)
{
matches++;
Debug.WriteLine($"Match {input}");
}
else
{
Debug.WriteLine($"Missmatch Actual value: {GetKey(prevInput, input)} - Predicted value: {lastPredictedValue}");
}
if (lyrOut.PredictiveCells.Count > 0)
{
var predictedInputValue = cls.GetPredictedInputValue(lyrOut.PredictiveCells.ToArray());
Debug.WriteLine($"Current Input: {input} \t| Predicted Input: {predictedInputValue}");
lastPredictedValue = predictedInputValue;
}
else
{
Debug.WriteLine($"NO CELLS PREDICTED for next cycle.");
}
prevInput = input.ToString();
}
//tm1.reset(mem);
double accuracy = (double)matches / (double)inputs.Length * 100.0;
Debug.WriteLine($"Cycle: {cycle}\tMatches={matches} of {inputs.Length}\t {accuracy}%");
if (accuracy == 100.0)
{
maxMatchCnt++;
Debug.WriteLine($"100% accuracy reched {maxMatchCnt} times.");
if (maxMatchCnt >= 20)
{
sw.Stop();
Debug.WriteLine($"Exit experiment in the stable state after 10 repeats with 100% of accuracy. Elapsed time: {sw.ElapsedMilliseconds / 1000 / 60} min.");
learn = false;
//var testInputs = new double[] { 0.0, 2.0, 3.0, 4.0, 5.0, 6.0, 5.0, 4.0, 3.0, 7.0, 1.0, 9.0, 12.0, 11.0, 0.0, 1.0 };
// C-0, D-1, E-2, F-3, G-4, H-5
//var testInputs = new double[] { 0.0, 0.0, 4.0, 4.0, 5.0, 5.0, 4.0, 3.0, 3.0, 2.0, 2.0, 1.0, 1.0, 0.0 };
//// Traverse the sequence and check prediction.
//foreach (var input in inputValues)
//{
// var lyrOut = layer1.Compute(input, learn) as ComputeCycle;
// predictedInputValue = cls.GetPredictedInputValue(lyrOut.predictiveCells.ToArray());
// Debug.WriteLine($"I={input} - P={predictedInputValue}");
//}
//
// Here we let the HTM predict seuence five times on its own.
// We start with last predicted value.
int cnt = 5 * inputValues.Count;
Debug.WriteLine("---- Start Predicting the Sequence -----");
// We take a random value to start somwhere in the sequence.
var predictedInputValue = inputValues[new Random().Next(0, inputValues.Count - 1)].ToString();
List <string> predictedValues = new List <string>();
while (--cnt > 0)
{
//var lyrOut = layer1.Compute(predictedInputValue, learn) as ComputeCycle;
var lyrOut = layer1.Compute(double.Parse(predictedInputValue[predictedInputValue.Length - 1].ToString()), learn) as ComputeCycle;
predictedInputValue = cls.GetPredictedInputValue(lyrOut.PredictiveCells.ToArray());
predictedValues.Add(predictedInputValue);
}
;
foreach (var item in predictedValues)
{
Debug.Write(item);
Debug.Write(" ,");
}
break;
}
}
else if (maxMatchCnt > 0)
{
Debug.WriteLine($"At 100% accuracy after {maxMatchCnt} repeats we get a drop of accuracy with {accuracy}. This indicates instable state. Learning will be continued.");
maxMatchCnt = 0;
}
}
Debug.WriteLine("---- cell state trace ----");
cls.TraceState($"cellState_MinPctOverlDuty-{p[KEY.MIN_PCT_OVERLAP_DUTY_CYCLES]}_MaxBoost-{p[KEY.MAX_BOOST]}.csv");
Debug.WriteLine("---- column state trace ----");
foreach (var input in activeColumnsLst)
{
using (StreamWriter colSw = new StreamWriter($"ColumState_MinPctOverlDuty-{p[KEY.MIN_PCT_OVERLAP_DUTY_CYCLES]}_MaxBoost-{p[KEY.MAX_BOOST]}_input-{input.Key}.csv"))
{
Debug.WriteLine($"------------ {input} ------------");
foreach (var actCols in input.Value)
{
Debug.WriteLine(Helpers.StringifyVector(actCols.ToArray()));
colSw.WriteLine(Helpers.StringifyVector(actCols.ToArray()));
}
}
}
Debug.WriteLine("------------ END ------------");
}
public void CategorySequenceExperiment()
{
bool learn = true;
Parameters p = Parameters.getAllDefaultParameters();
p.Set(KEY.RANDOM, new ThreadSafeRandom(42));
p.Set(KEY.INPUT_DIMENSIONS, new int[] { 100 });
p.Set(KEY.CELLS_PER_COLUMN, 30);
string[] categories = new string[] { "A", "B", "C", "D" };
//string[] categories = new string[] { "A", "B", "C", "D", "E", "F", "G", "H", "I", "K", "L" , "M", "O", "P", "Q", "R", "S", "T", "U", "V", "W", "X", "Y", "Z", "Ö" };
CortexNetwork net = new CortexNetwork("my cortex");
List <CortexRegion> regions = new List <CortexRegion>();
CortexRegion region0 = new CortexRegion("1st Region");
regions.Add(region0);
SpatialPoolerMT sp1 = new SpatialPoolerMT();
TemporalMemory tm1 = new TemporalMemory();
var mem = new Connections();
p.apply(mem);
sp1.Init(mem, UnitTestHelpers.GetMemory());
tm1.Init(mem);
Dictionary <string, object> settings = new Dictionary <string, object>();
//settings.Add("W", 25);
settings.Add("N", 100);
//settings.Add("Radius", 1);
EncoderBase encoder = new CategoryEncoder(categories, settings);
//encoder.Encode()
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
region0.AddLayer(layer1);
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp1);
//layer1.HtmModules.Add(tm1);
//layer1.Compute();
//IClassifier<string, ComputeCycle> cls = new HtmClassifier<string, ComputeCycle>();
HtmClassifier <string, ComputeCycle> cls = new HtmClassifier <string, ComputeCycle>();
HtmUnionClassifier <string, ComputeCycle> cls1 = new HtmUnionClassifier <string, ComputeCycle>();
//string[] inputs = new string[] { "A", "B", "C", "D" };
string[] inputs = new string[] { "A", "B", "C", "D" };
//
// This trains SP.
foreach (var input in inputs)
{
Debug.WriteLine($" ** {input} **");
for (int i = 0; i < 3; i++)
{
var lyrOut = layer1.Compute((object)input, learn) as ComputeCycle;
}
}
// Here we add TM module to the layer.
layer1.HtmModules.Add("tm", tm1);
//
// Now, training with SP+TM. SP is pretrained on pattern.
for (int i = 0; i < 200; i++)
{
foreach (var input in inputs)
{
var lyrOut = layer1.Compute(input, learn) as ComputeCycle;
//cls1.Learn(input, lyrOut.activeCells.ToArray(), learn);
//Debug.WriteLine($"Current Input: {input}");
cls.Learn(input, lyrOut.ActiveCells.ToArray());
Debug.WriteLine($"Current Input: {input}");
if (learn == false)
{
Debug.WriteLine($"Predict Input When Not Learn: {cls.GetPredictedInputValue(lyrOut.PredictiveCells.ToArray())}");
}
else
{
Debug.WriteLine($"Predict Input: {cls.GetPredictedInputValue(lyrOut.PredictiveCells.ToArray())}");
}
Debug.WriteLine("-----------------------------------------------------------\n----------------------------------------------------------");
}
if (i == 10)
{
Debug.WriteLine("Stop Learning From Here----------------------------");
learn = false;
}
// tm1.reset(mem);
}
Debug.WriteLine("------------------------------------------------------------------------\n----------------------------------------------------------------------------");
/*
* learn = false;
* for (int i = 0; i < 19; i++)
* {
* foreach (var input in inputs)
* {
* layer1.Compute((object)input, learn);
* }
* }
*/
}
private void RunExperiment(int inputBits, HtmConfig cfgL4, EncoderBase encoder, List <double> inputValues, HtmConfig cfgL2)
{
Stopwatch swL2 = new Stopwatch();
//int maxMatchCnt = 0;
bool learn = true;
bool isSP1Stable = false;
bool isSP2STable = false;
var memL4 = new Connections(cfgL4);
var memL2 = new Connections(cfgL2);
var numInputs = inputValues.Distinct <double>().ToList().Count;
HtmClassifier <string, ComputeCycle> cls = new HtmClassifier <string, ComputeCycle>();
layerL4 = new CortexLayer <object, object>("L4");
layerL2 = new CortexLayer <object, object>("L2");
tm4 = new TemporalMemoryMT();
tm2 = new TemporalMemoryMT();
//
// HPC for Layer 4 SP
HomeostaticPlasticityController hpa_sp_L4 = new HomeostaticPlasticityController(memL4, numInputs * 50, (isStable, numPatterns, actColAvg, seenInputs) =>
{
if (isStable)
{
Debug.WriteLine($"SP L4 STABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
else
{
Debug.WriteLine($"SP L4 INSTABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
learn = isSP1Stable = isStable;
//cls.ClearState();
}, numOfCyclesToWaitOnChange: 50);
//
// HPC for Layer 2 SP
HomeostaticPlasticityController hpa_sp_L2 = new HomeostaticPlasticityController(memL2, numInputs * 50, (isStable, numPatterns, actColAvg, seenInputs) =>
{
if (isStable)
{
Debug.WriteLine($"SP L2 STABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
else
{
Debug.WriteLine($"SP L2 INSTABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
learn = isSP2STable = isStable;
//cls.ClearState();
}, numOfCyclesToWaitOnChange: 50);
SpatialPooler sp4 = new SpatialPoolerMT(hpa_sp_L4);
SpatialPooler sp2 = new SpatialPoolerMT(hpa_sp_L2);
sp4.Init(memL4);
sp2.Init(memL2);
// memL2.TraceInputPotential();
tm4.Init(memL4);
tm2.Init(memL2);
layerL4.HtmModules.Add("encoder", encoder);
layerL4.HtmModules.Add("sp", sp4);
layerL4.HtmModules.Add("tm", tm4);
layerL2.HtmModules.Add("sp", sp2);
layerL2.HtmModules.Add("tm", tm2);
int[] inpCellsL4ToL2 = new int[cfgL4.CellsPerColumn * cfgL4.NumColumns];
double[] inputs = inputValues.ToArray();
int[] prevActiveCols = new int[0];
int cycle = 0;
int matches = 0;
// string lastPredictedValue = "0";
int maxCycles = 3500;
int maxPrevInputs = inputValues.Count - 1;
List <string> previousInputs = new List <string>();
//
// Training SP at Layer 4 to get stable. New-born stage.
//
using (StreamWriter swL4Sdrs = new StreamWriter($"L4-SDRs-in_{cfgL2.NumInputs}-col_{cfgL2.NumColumns}-r_{cfgL2.PotentialRadius}.txt"))
{
using (StreamWriter sw = new StreamWriter($"in_{cfgL2.NumInputs}-col_{cfgL2.NumColumns}-r_{cfgL2.PotentialRadius}.txt"))
{
for (int i = 0; i < maxCycles; i++)
{
matches = 0;
cycle++;
Debug.WriteLine($"-------------- Newborn Cycle {cycle} at L4 SP region ---------------");
foreach (var input in inputs)
{
Debug.WriteLine($" INPUT: '{input}'\tCycle:{cycle}");
Debug.Write("L4: ");
var lyrOut = layerL4.Compute(input, learn);
InitArray(inpCellsL4ToL2, 0);
if (isSP1Stable)
{
var cellSdrL4Indexes = memL4.ActiveCells.Select(c => c.Index).ToArray();
// Write SDR as output of L4 and input of L2
swL4Sdrs.WriteLine($"{input} - {Helpers.StringifyVector(cellSdrL4Indexes)}");
// Set the output active cell array
ArrayUtils.SetIndexesTo(inpCellsL4ToL2, cellSdrL4Indexes, 1);
Debug.Write("L2: ");
swL2.Restart();
layerL2.Compute(inpCellsL4ToL2, true);
swL2.Stop();
Debug.WriteLine($"{swL2.ElapsedMilliseconds / 1000}");
sw.WriteLine($"{swL2.ElapsedMilliseconds / 1000}");
sw.Flush();
Debug.WriteLine($"L4 out sdr: {Helpers.StringifyVector(cellSdrL4Indexes)}");
var overlaps = ArrayUtils.IndexWhere(memL2.Overlaps, o => o > 0);
var strOverlaps = Helpers.StringifyVector(overlaps);
Debug.WriteLine($"Potential columns: {overlaps.Length}, overlaps: {strOverlaps}");
}
if (isSP1Stable && isSP2STable)
{
break;
}
}
}
}
}
Debug.WriteLine($"-------------- L4 SP region is {isSP1Stable} ---------------");
//layerL4.HtmModules.Add("tm", tm4);
// SP+TM at L4
for (int i = 0; i < maxCycles; i++)
{
matches -= 0;
cycle++;
Debug.WriteLine($"-------------- L4 TM Train region Cycle {cycle} ---------------");
foreach (var input in inputs)
{
Debug.WriteLine($"-------------- {input} ---------------");
var lyrOut = layerL4.Compute(input, learn) as ComputeCycle;
previousInputs.Add(input.ToString());
if (previousInputs.Count > (maxPrevInputs + 1))
{
previousInputs.RemoveAt(0);
}
if (previousInputs.Count < maxPrevInputs)
{
continue;
}
if (lyrOut.ActiveCells.Count == lyrOut.WinnerCells.Count)
{
/*var activeColumns = L4.GetResult("sp") as int[];
* foreach (var item in activeColumns)
* {
* L2.Compute(item, true);
* }*/
// Reset tha array
InitArray(inpCellsL4ToL2, 0);
// Set the output active cell array
ArrayUtils.SetIndexesTo(inpCellsL4ToL2, memL4.ActiveCells.Select(c => c.Index).ToArray(), 1);
// 4102,25072, 25363, 25539, 25738, 25961, 26009, 26269, 26491, 26585, 26668, 26920, 26934, 27040, 27107, 27262, 27392, 27826, 27948, 28174, 28243, 28270, 28294, 28308, 28429, 28577, 28671, 29139, 29618, 29637, 29809, 29857, 29897, 29900, 29969, 30057, 30727, 31111, 49805, 49972,
layerL2.Compute(inpCellsL4ToL2, true);
/*foreach (var item in lyrOut.ActiveCells)
* {
* L2.Compute(item, true);
* }*/
//var activeCell = Helpers.StringifyVector(lyrOut.ActiveCells.Select(c => c.Index).ToArray());
//L2.Compute(activeCell, true);
}
}
}
}
private void RunExperiment(int inputBits, HtmConfig cfgL4, EncoderBase encoder, List <double> inputValues, HtmConfig cfgL2)
{
Stopwatch swL2 = new Stopwatch();
int maxMatchCnt = 0;
bool learn = true;
bool isSP4Stable = false;
bool isSP2STable = false;
var memL4 = new Connections(cfgL4);
var memL2 = new Connections(cfgL2);
var numInputs = inputValues.Distinct <double>().ToList().Count;
HtmClassifier <string, ComputeCycle> cls = new HtmClassifier <string, ComputeCycle>();
layerL4 = new CortexLayer <object, object>("L4");
layerL2 = new CortexLayer <object, object>("L2");
tm4 = new TemporalMemoryMT();
tm2 = new TemporalMemoryMT();
// HPC for Layer 4 SP
HomeostaticPlasticityController hpa_sp_L4 = new HomeostaticPlasticityController(memL4, numInputs * 50, (isStable, numPatterns, actColAvg, seenInputs) =>
{
if (isStable)
{
Debug.WriteLine($"SP L4 STABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
else
{
Debug.WriteLine($"SP L4 INSTABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
learn = isSP4Stable = isStable;
}, numOfCyclesToWaitOnChange: 50);
// HPC for Layer 2 SP
HomeostaticPlasticityController hpa_sp_L2 = new HomeostaticPlasticityController(memL2, numInputs * 50, (isStable, numPatterns, actColAvg, seenInputs) =>
{
if (isStable)
{
Debug.WriteLine($"SP L2 STABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
else
{
Debug.WriteLine($"SP L2 INSTABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
learn = isSP2STable = isStable;
cls.ClearState();
}, numOfCyclesToWaitOnChange: 50);
SpatialPooler sp4 = new SpatialPoolerMT(hpa_sp_L4);
SpatialPooler sp2 = new SpatialPoolerMT(hpa_sp_L2);
sp4.Init(memL4);
sp2.Init(memL2);
// memL2.TraceInputPotential();
tm4.Init(memL4);
tm2.Init(memL2);
layerL4.HtmModules.Add("encoder", encoder);
layerL4.HtmModules.Add("sp", sp4);
layerL4.HtmModules.Add("tm", tm4);
layerL2.HtmModules.Add("sp", sp2);
layerL2.HtmModules.Add("tm", tm2);
int[] inpCellsL4ToL2 = new int[cfgL4.CellsPerColumn * cfgL4.NumColumns];
double[] inputs = inputValues.ToArray();
int[] prevActiveCols = new int[0];
int cycle = 0;
int matches = 0;
string lastPredictedValue = "0";
int maxCycles = 3500;
int maxPrevInputs = inputValues.Count - 1;
List <string> previousInputs = new List <string>();
//
// Training SP at Layer 4 to get stable. New-born stage.
//
using (StreamWriter swL4Sdrs = new StreamWriter($"L4-SDRs-in_{cfgL2.NumInputs}-col_{cfgL2.NumColumns}-r_{cfgL2.PotentialRadius}.txt"))
{
using (StreamWriter sw = new StreamWriter($"in_{cfgL2.NumInputs}-col_{cfgL2.NumColumns}-r_{cfgL2.PotentialRadius}.txt"))
{
for (int i = 0; i < maxCycles; i++)
{
matches = 0;
cycle = i;
Debug.WriteLine($"-------------- Newborn Cycle {cycle} at L4 SP region ---------------");
foreach (var input in inputs)
{
Debug.WriteLine($" INPUT: '{input}'\tCycle:{cycle}");
Debug.Write("L4: ");
//L4 SP pre train
layerL4.Compute(input, learn);
InitArray(inpCellsL4ToL2, 0);
if (isSP4Stable)
{
var cellSdrL4Indexes = memL4.ActiveCells.Select(c => c.Index).ToArray();
// Write SDR as output of L4 and input of L2
swL4Sdrs.WriteLine($"{input} - {Helpers.StringifyVector(cellSdrL4Indexes)}");
// Set the output active cell array
ArrayUtils.SetIndexesTo(inpCellsL4ToL2, cellSdrL4Indexes, 1);
Debug.WriteLine($"L4 out sdr: {Helpers.StringifyVector(cellSdrL4Indexes)}");
Debug.WriteLine("L2: ");
swL2.Restart();
/// <summary>
/// This part is for to make SP of Layer2 stable thourgh help
/// of HPC Boosting Algo from new born stage.
/// </summary>
layerL2.Compute(inpCellsL4ToL2, true);
swL2.Stop();
Debug.WriteLine($"{swL2.ElapsedMilliseconds / 1000}");
sw.WriteLine($"{swL2.ElapsedMilliseconds / 1000}");
sw.Flush();
var overlaps = ArrayUtils.IndexWhere(memL2.Overlaps, o => o > 0);
var strOverlaps = Helpers.StringifyVector(overlaps);
Debug.WriteLine($"Potential columns: {overlaps.Length}, overlaps: {strOverlaps}");
}
}
if (isSP4Stable && isSP2STable)
{
break;
}
}
}
}
// SP+TM at L4
for (int i = 0; i < maxCycles; i++)
{
matches = 0;
cycle = i;
Debug.WriteLine($"-------------- L4 TM Train region Cycle {cycle} ---------------");
foreach (var input in inputs)
{
Debug.WriteLine($"-------------- {input} ---------------");
var layerL4Out = layerL4.Compute(input, learn) as ComputeCycle;
previousInputs.Add(input.ToString());
if (previousInputs.Count > (maxPrevInputs + 1))
{
previousInputs.RemoveAt(0);
}
if (previousInputs.Count < maxPrevInputs)
{
continue;
}
string key = GetKey(previousInputs, input);
List <Cell> actCells;
if (layerL4Out.ActiveCells.Count == layerL4Out.WinnerCells.Count)
{
// SP+TM at L2
Debug.WriteLine($"-------------- L2 TM Train region Cycle {cycle} ---------------");
// Reset tha array
InitArray(inpCellsL4ToL2, 0);
var cellSdrL4Indexes = memL4.ActiveCells.Select(c => c.Index).ToArray();
// Set the output active cell array
ArrayUtils.SetIndexesTo(inpCellsL4ToL2, cellSdrL4Indexes, 1);
var layerL2Out = layerL2.Compute(inpCellsL4ToL2, true) as ComputeCycle;
int[] overlaps = ArrayUtils.IndexWhere(memL2.Overlaps, o => o > 0);
var strOverlaps = Helpers.StringifyVector(overlaps);
Debug.WriteLine($"Potential columns: {overlaps.Length}, overlaps: {strOverlaps}");
if (layerL2Out.ActiveCells.Count == layerL2Out.WinnerCells.Count)
{
actCells = layerL2Out.ActiveCells;
}
else
{
actCells = layerL2Out.WinnerCells;
}
cls.Learn(key, actCells.ToArray());
if (key == lastPredictedValue)
{
matches++;
Debug.WriteLine($"Match. Actual value: {key} - Predicted value: {lastPredictedValue}");
}
else
{
Debug.WriteLine($"Missmatch! Actual value: {key} - Predicted value: {lastPredictedValue}");
}
if (layerL2Out.PredictiveCells.Count > 0)
{
var predictedInputValue = cls.GetPredictedInputValue(layerL2Out.PredictiveCells.ToArray());
Debug.WriteLine($"Current Input: {input} \t| Predicted Input: {predictedInputValue}");
lastPredictedValue = predictedInputValue;
}
else
{
Debug.WriteLine($"NO CELLS PREDICTED for next cycle.");
lastPredictedValue = String.Empty;
}
}
}
double accuracy = (double)matches / (double)inputs.Length * 100.0;
Debug.WriteLine($"Cycle: {cycle}\tMatches={matches} of {inputs.Length}\t {accuracy}%");
if (accuracy >= 100.0)
{
maxMatchCnt++;
Debug.WriteLine($"100% accuracy reched {maxMatchCnt} times.");
//
// Experiment is completed if we are 20 cycles long at the 100% accuracy.
if (maxMatchCnt >= 20)
{
Debug.WriteLine($"Exit experiment in the stable state after 20 repeats with 100% of accuracy.");
learn = false;
break;
}
}
else if (maxMatchCnt > 0)
{
Debug.WriteLine($"At 100% accuracy after {maxMatchCnt} repeats we get a drop of accuracy with {accuracy}. This indicates instable state. Learning will be continued.");
maxMatchCnt = 0;
}
}
}
/// <summary>
///
/// </summary>
private static void RunExperiment(int inputBits, HtmConfig cfg, EncoderBase encoder, List <double> inputValues)
{
Stopwatch sw = new Stopwatch();
sw.Start();
int maxMatchCnt = 0;
bool learn = true;
CortexNetwork net = new CortexNetwork("my cortex");
List <CortexRegion> regions = new List <CortexRegion>();
CortexRegion region0 = new CortexRegion("1st Region");
regions.Add(region0);
var mem = new Connections(cfg);
bool isInStableState;
HtmClassifier <string, ComputeCycle> cls = new HtmClassifier <string, ComputeCycle>();
var numInputs = inputValues.Distinct <double>().ToList().Count;
TemporalMemory tm1 = new TemporalMemory();
HomeostaticPlasticityController hpa = new HomeostaticPlasticityController(mem, numInputs * 55, (isStable, numPatterns, actColAvg, seenInputs) =>
{
if (isStable)
{
// Event should be fired when entering the stable state.
Debug.WriteLine($"STABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
else
{
// Ideal SP should never enter unstable state after stable state.
Debug.WriteLine($"INSTABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
if (numPatterns != numInputs)
{
throw new InvalidOperationException("Stable state must observe all input patterns");
}
isInStableState = true;
cls.ClearState();
tm1.Reset(mem);
}, numOfCyclesToWaitOnChange: 25);
SpatialPoolerMT sp1 = new SpatialPoolerMT(hpa);
sp1.Init(mem, new DistributedMemory()
{
ColumnDictionary = new InMemoryDistributedDictionary <int, NeoCortexApi.Entities.Column>(1),
});
tm1.Init(mem);
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
region0.AddLayer(layer1);
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp1);
layer1.HtmModules.Add("tm", tm1);
double[] inputs = inputValues.ToArray();
int[] prevActiveCols = new int[0];
int cycle = 0;
int matches = 0;
string lastPredictedValue = "0";
String prediction = null;
Dictionary <double, List <List <int> > > activeColumnsLst = new Dictionary <double, List <List <int> > >();
foreach (var input in inputs)
{
if (activeColumnsLst.ContainsKey(input) == false)
{
activeColumnsLst.Add(input, new List <List <int> >());
}
}
int maxCycles = 3500;
int maxPrevInputs = inputValues.Count - 1;
List <string> previousInputs = new List <string>();
previousInputs.Add("-1.0");
//
// Now training with SP+TM. SP is pretrained on the given input pattern.
for (int i = 0; i < maxCycles; i++)
{
matches = 0;
cycle++;
Debug.WriteLine($"-------------- Cycle {cycle} ---------------");
foreach (var input in inputs)
{
Debug.WriteLine($"-------------- {input} ---------------");
var lyrOut = layer1.Compute(input, learn) as ComputeCycle;
var activeColumns = layer1.GetResult("sp") as int[];
activeColumnsLst[input].Add(activeColumns.ToList());
previousInputs.Add(input.ToString());
if (previousInputs.Count > (maxPrevInputs + 1))
{
previousInputs.RemoveAt(0);
}
string key = GetKey(previousInputs, input);
cls.Learn(key, lyrOut.ActiveCells.ToArray());
if (learn == false)
{
Debug.WriteLine($"Inference mode");
}
Debug.WriteLine($"Col SDR: {Helpers.StringifyVector(lyrOut.ActivColumnIndicies)}");
Debug.WriteLine($"Cell SDR: {Helpers.StringifyVector(lyrOut.ActiveCells.Select(c => c.Index).ToArray())}");
if (key == lastPredictedValue)
{
matches++;
Debug.WriteLine($"Match. Actual value: {key} - Predicted value: {lastPredictedValue}");
}
else
{
Debug.WriteLine($"Missmatch! Actual value: {key} - Predicted value: {lastPredictedValue}");
}
if (lyrOut.PredictiveCells.Count > 0)
{
var predictedInputValue = cls.GetPredictedInputValues(lyrOut.PredictiveCells.ToArray(), 3);
Debug.WriteLine($"Current Input: {input}");
Debug.WriteLine("The predictions with similarity greater than 50% are");
foreach (var t in predictedInputValue)
{
if (t.Similarity >= (double)50.00)
{
Debug.WriteLine($"Predicted Input: {string.Join(", ", t.PredictedInput)},\tSimilarity Percentage: {string.Join(", ", t.Similarity)}, \tNumber of Same Bits: {string.Join(", ", t.NumOfSameBits)}");
}
}
lastPredictedValue = predictedInputValue.First().PredictedInput;
}
else
{
Debug.WriteLine($"NO CELLS PREDICTED for next cycle.");
lastPredictedValue = String.Empty;
}
}
double accuracy = (double)matches / (double)inputs.Length * 100.0;
Debug.WriteLine($"Cycle: {cycle}\tMatches={matches} of {inputs.Length}\t {accuracy}%");
if (accuracy == 100.0)
{
maxMatchCnt++;
Debug.WriteLine($"100% accuracy reched {maxMatchCnt} times.");
if (maxMatchCnt >= 30)
{
sw.Stop();
Debug.WriteLine($"Exit experiment in the stable state after 30 repeats with 100% of accuracy. Elapsed time: {sw.ElapsedMilliseconds / 1000 / 60} min.");
learn = false;
break;
}
}
else if (maxMatchCnt > 0)
{
Debug.WriteLine($"At 100% accuracy after {maxMatchCnt} repeats we get a drop of accuracy with {accuracy}. This indicates instable state. Learning will be continued.");
maxMatchCnt = 0;
}
}
Debug.WriteLine("---- cell state trace ----");
cls.TraceState($"cellState_MinPctOverlDuty-{cfg.MinPctOverlapDutyCycles}_MaxBoost-{cfg.MaxBoost}.csv");
Debug.WriteLine("---- Spatial Pooler column state ----");
foreach (var input in activeColumnsLst)
{
using (StreamWriter colSw = new StreamWriter($"ColumState_MinPctOverlDuty-{cfg.MinPctOverlapDutyCycles}_MaxBoost-{cfg.MaxBoost}_input-{input.Key}.csv"))
{
Debug.WriteLine($"------------ {input.Key} ------------");
foreach (var actCols in input.Value)
{
Debug.WriteLine(Helpers.StringifyVector(actCols.ToArray()));
colSw.WriteLine(Helpers.StringifyVector(actCols.ToArray()));
}
}
}
Debug.WriteLine("------------ END ------------");
Console.WriteLine("\n Please enter a number that has been learnt");
int inputNumber = Convert.ToInt16(Console.ReadLine());
Inference(inputNumber, false, layer1, cls);
}
/// <summary>
///
/// </summary>
private void RunExperiment(int inputBits, HtmConfig cfg, EncoderBase encoder, List <double> inputValues)
{
Stopwatch sw = new Stopwatch();
sw.Start();
int maxMatchCnt = 0;
bool learn = true;
var mem = new Connections(cfg);
bool isInStableState = false;
HtmClassifier <string, ComputeCycle> cls = new HtmClassifier <string, ComputeCycle>();
var numInputs = inputValues.Distinct <double>().ToList().Count;
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
TemporalMemory tm = new TemporalMemory();
HomeostaticPlasticityController hpa = new HomeostaticPlasticityController(mem, numInputs * 150, (isStable, numPatterns, actColAvg, seenInputs) =>
{
if (isStable)
{
// Event should be fired when entering the stable state.
Debug.WriteLine($"STABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
else
{
// Ideal SP should never enter unstable state after stable state.
Debug.WriteLine($"INSTABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
// We are not learning in instable state.
learn = isInStableState = isStable;
//if (isStable && layer1.HtmModules.ContainsKey("tm") == false)
// layer1.HtmModules.Add("tm", tm);
// Clear all learned patterns in the classifier.
cls.ClearState();
// Clear active and predictive cells.
//tm.Reset(mem);
}, numOfCyclesToWaitOnChange: 50);
SpatialPoolerMT sp = new SpatialPoolerMT(hpa);
sp.Init(mem);
tm.Init(mem);
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp);
double[] inputs = inputValues.ToArray();
int[] prevActiveCols = new int[0];
int cycle = 0;
int matches = 0;
string lastPredictedValue = "0";
//Dictionary<double, List<List<int>>> activeColumnsLst = new Dictionary<double, List<List<int>>>();
//foreach (var input in inputs)
//{
// if (activeColumnsLst.ContainsKey(input) == false)
// activeColumnsLst.Add(input, new List<List<int>>());
//}
int maxCycles = 3500;
int maxPrevInputs = inputValues.Count - 1;
List <string> previousInputs = new List <string>();
previousInputs.Add("-1.0");
//
// Training SP to get stable. New-born stage.
//
for (int i = 0; i < maxCycles; i++)
{
matches = 0;
cycle++;
Debug.WriteLine($"-------------- Newborn Cycle {cycle} ---------------");
foreach (var input in inputs)
{
Debug.WriteLine($" -- {input} --");
var lyrOut = layer1.Compute(input, learn);
if (isInStableState)
{
break;
}
}
if (isInStableState)
{
break;
}
}
layer1.HtmModules.Add("tm", tm);
//
// Now training with SP+TM. SP is pretrained on the given input pattern set.
for (int i = 0; i < maxCycles; i++)
{
matches = 0;
cycle++;
Debug.WriteLine($"-------------- Cycle {cycle} ---------------");
foreach (var input in inputs)
{
Debug.WriteLine($"-------------- {input} ---------------");
var lyrOut = layer1.Compute(input, learn) as ComputeCycle;
// lyrOut is null when the TM is added to the layer inside of HPC callback by entering of the stable state.
//if (isInStableState && lyrOut != null)
{
var activeColumns = layer1.GetResult("sp") as int[];
//layer2.Compute(lyrOut.WinnerCells, true);
//activeColumnsLst[input].Add(activeColumns.ToList());
previousInputs.Add(input.ToString());
if (previousInputs.Count > (maxPrevInputs + 1))
{
previousInputs.RemoveAt(0);
}
// In the pretrained SP with HPC, the TM will quickly learn cells for patterns
// In that case the starting sequence 4-5-6 might have the sam SDR as 1-2-3-4-5-6,
// Which will result in returning of 4-5-6 instead of 1-2-3-4-5-6.
// HtmClassifier allways return the first matching sequence. Because 4-5-6 will be as first
// memorized, it will match as the first one.
if (previousInputs.Count < maxPrevInputs)
{
continue;
}
string key = GetKey(previousInputs, input);
List <Cell> actCells;
if (lyrOut.ActiveCells.Count == lyrOut.WinnerCells.Count)
{
actCells = lyrOut.ActiveCells;
}
else
{
actCells = lyrOut.WinnerCells;
}
cls.Learn(key, actCells.ToArray());
if (learn == false)
{
Debug.WriteLine($"Inference mode");
}
Debug.WriteLine($"Col SDR: {Helpers.StringifyVector(lyrOut.ActivColumnIndicies)}");
Debug.WriteLine($"Cell SDR: {Helpers.StringifyVector(actCells.Select(c => c.Index).ToArray())}");
if (key == lastPredictedValue)
{
matches++;
Debug.WriteLine($"Match. Actual value: {key} - Predicted value: {lastPredictedValue}");
}
else
{
Debug.WriteLine($"Missmatch! Actual value: {key} - Predicted value: {lastPredictedValue}");
}
if (lyrOut.PredictiveCells.Count > 0)
{
var predictedInputValue = cls.GetPredictedInputValue(lyrOut.PredictiveCells.ToArray());
Debug.WriteLine($"Current Input: {input} \t| Predicted Input: {predictedInputValue}");
lastPredictedValue = predictedInputValue;
}
else
{
Debug.WriteLine($"NO CELLS PREDICTED for next cycle.");
lastPredictedValue = String.Empty;
}
}
}
// The brain does not do that this way, so we don't use it.
// tm1.reset(mem);
double accuracy = (double)matches / (double)inputs.Length * 100.0;
Debug.WriteLine($"Cycle: {cycle}\tMatches={matches} of {inputs.Length}\t {accuracy}%");
if (accuracy == 100.0)
{
maxMatchCnt++;
Debug.WriteLine($"100% accuracy reched {maxMatchCnt} times.");
//
// Experiment is completed if we are 30 cycles long at the 100% accuracy.
if (maxMatchCnt >= 30)
{
sw.Stop();
Debug.WriteLine($"Exit experiment in the stable state after 30 repeats with 100% of accuracy. Elapsed time: {sw.ElapsedMilliseconds / 1000 / 60} min.");
learn = false;
break;
}
}
else if (maxMatchCnt > 0)
{
Debug.WriteLine($"At 100% accuracy after {maxMatchCnt} repeats we get a drop of accuracy with {accuracy}. This indicates instable state. Learning will be continued.");
maxMatchCnt = 0;
}
}
Debug.WriteLine("------------ END ------------");
}
private void RunExperiment(int inputBits, HtmConfig cfgL4, EncoderBase encoder, List <double> inputValues, HtmConfig cfgL2)
{
Stopwatch swL2 = new Stopwatch();
int maxMatchCnt = 0;
bool learn = true;
bool isSP4Stable = false;
bool isSP2STable = false;
Connections memL4 = new Connections(cfgL4);
Connections memL2 = new Connections(cfgL2);
int numInputs = inputValues.Distinct <double>().ToList().Count;
HtmClassifier <string, ComputeCycle> cls = new HtmClassifier <string, ComputeCycle>();
layerL4 = new CortexLayer <object, object>("L4");
layerL2 = new CortexLayer <object, object>("L2");
//tm4 = new TemporalMemoryMT();
//tm2 = new TemporalMemoryMT();
tm4 = new TemporalMemory();
tm2 = new TemporalMemory();
//
// HPC for Layer 4 SP
HomeostaticPlasticityController hpa_sp_L4 = new HomeostaticPlasticityController(memL4, numInputs * 50, (isStable, numPatterns, actColAvg, seenInputs) =>
{
if (isStable)
{
Debug.WriteLine($"SP L4 STABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
else
{
Debug.WriteLine($"SP L4 INSTABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
learn = isSP4Stable = isStable;
cls.ClearState();
}, numOfCyclesToWaitOnChange: 50);
//
// HPC for Layer 2 SP
HomeostaticPlasticityController hpa_sp_L2 = new HomeostaticPlasticityController(memL2, numInputs * 50, (isStable, numPatterns, actColAvg, seenInputs) =>
{
if (isStable)
{
Debug.WriteLine($"SP L2 STABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
else
{
Debug.WriteLine($"SP L2 INSTABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
learn = isSP2STable = isStable;
cls.ClearState();
}, numOfCyclesToWaitOnChange: 50);
SpatialPooler sp4 = new SpatialPooler(hpa_sp_L4);
SpatialPooler sp2 = new SpatialPooler(hpa_sp_L2);
sp4.Init(memL4);
sp2.Init(memL2);
// memL2.TraceInputPotential();
tm4.Init(memL4);
tm2.Init(memL2);
layerL4.HtmModules.Add("encoder", encoder);
layerL4.HtmModules.Add("sp", sp4);
layerL4.HtmModules.Add("tm", tm4);
layerL2.HtmModules.Add("sp", sp2);
layerL2.HtmModules.Add("tm", tm2);
int[] inpCellsL4ToL2 = new int[cfgL4.CellsPerColumn * cfgL4.NumColumns];
double[] inputs = inputValues.ToArray();
int[] prevActiveCols = new int[0];
int cycle = 0;
int matches = 0;
string lastPredictedValue = "0";
int maxCycles = 3500;
int maxPrevInputs = inputValues.Count - 1;
List <string> previousInputs = new List <string>();
//
// Training SP at Layer 4 to get stable. New-born stage.
//
using (StreamWriter swL4Sdrs = new StreamWriter($"L4-SDRs-in_{cfgL2.NumInputs}-col_{cfgL2.NumColumns}-r_{cfgL2.PotentialRadius}.txt"))
{
using (StreamWriter sw = new StreamWriter($"in_{cfgL2.NumInputs}-col_{cfgL2.NumColumns}-r_{cfgL2.PotentialRadius}.txt"))
{
for (int i = 0; i < maxCycles; i++)
{
matches = 0;
cycle = i;
Debug.WriteLine($"-------------- Newborn Cycle {cycle} at L4 SP region ---------------");
foreach (double input in inputs)
{
Debug.WriteLine($" INPUT: '{input}'\t Cycle:{cycle}");
Debug.Write("L4: ");
object lyrOut = layerL4.Compute(input, learn);
int[] activeColumns = layerL4.GetResult("sp") as int[];
int[] cellSdrL4Indexes = memL4.ActiveCells.Select(c => c.Index).ToArray();
Debug.WriteLine($"L4out Active Coloumn for input: {input}: {Helpers.StringifyVector(activeColumns)}");
Debug.WriteLine($"L4out SDR for input: {input}: {Helpers.StringifyVector(cellSdrL4Indexes)}");
if (isSP4Stable)
{
/// <summary>
/// Checking Layer4 SP is giving similar or different
/// Active Cell Sdr Indexes After it reaches to stable state.
/// This portion is actuallly to hold all acive cell sdr
/// indexes after Layer 4 SP reaches at stable state via HPC.
///
/// But why we have done this?
///
/// Actually, In Necortex api we have obeserved during severel
/// experiments that whenvever Layer4 SP reaches to STABLE sate
/// it doesnt give us smilar pattern of Active Cell SDR Indexes
/// for each particular input data.
///
/// Instead active cell sdr patern of L4 varried though it has reached
/// to stable sate!
///
/// So we want to obeserve whether Layer 4 SP is giving similar active cell sdr indexes
/// or different acrive cell sdr indexes after it reaches to stable state.
///
/// If we receive similar acrive cell sdr indexes from Layer 4 sp after it reaches
/// to stable state then do train Layer 2 sp by as usual process in NeocortexApi by
/// calling Layer4.Compute().
///
/// But if we receive different active cell sdr indexes then we will train Layer 2 sp
/// from L4_ActiveCell_sdr_log so that during training
/// Layer 2 SP gets similar stable active cell sdr indexes of layer4
/// from that dictionary. As a result, L2 SP will get similar sequence
/// of active cell sdr indexes during SP Tarining and reach to STABLE state
/// </summary>
Array.Sort(cellSdrL4Indexes);
if (!L4_ActiveCell_sdr_log.ContainsKey(input))
{
L4_ActiveCell_sdr_log.Add(input, cellSdrL4Indexes);
}
else
{
if (L4_ActiveCell_sdr_log[input].SequenceEqual(cellSdrL4Indexes))
{
Debug.WriteLine($"Layer4.Compute() is giving similar cell sdr indexes for input : {input} after reaching to stable state");
isSimilar_L4_active_cell_sdr = true;
}
else
{
isSimilar_L4_active_cell_sdr = false;
Debug.WriteLine($"Layer4.Compute() is giving different cell sdr indexes for input : {input} after reaching to stable state");
Debug.WriteLine($"Sdr Mismatch with L4_ActiveCell_sdr_log after reaching to stable state");
Debug.WriteLine($" L4_ActiveCell_sdr_log output for input {input}: { Helpers.StringifyVector(L4_ActiveCell_sdr_log[input])}");
Debug.WriteLine($"L4 out sdr input:{input} {Helpers.StringifyVector(cellSdrL4Indexes)}");
//Debug.WriteLine($"L4 out ac input: {input}: {Helpers.StringifyVector(activeColumns)}");
}
}
if (!isSimilar_L4_active_cell_sdr)
{
cellSdrL4Indexes = L4_ActiveCell_sdr_log[input];
}
//
// Training SP at Layer 2 to get stable. New-born stage.
//
// Write SDR as output of L4 and input of L2
// swL4Sdrs.WriteLine($"{input} - {Helpers.StringifyVector(cellSdrL4Indexes)}");
// Set the output active cell array
InitArray(inpCellsL4ToL2, 0);
ArrayUtils.SetIndexesTo(inpCellsL4ToL2, cellSdrL4Indexes, 1);
Debug.WriteLine($"L4 cell sdr to L2 SP Train for Input {input}: ");
layerL2.Compute(inpCellsL4ToL2, true);
int[] overlaps = ArrayUtils.IndexWhere(memL2.Overlaps, o => o > 0);
string strOverlaps = Helpers.StringifyVector(overlaps);
Debug.WriteLine($"Potential columns: {overlaps.Length}, overlaps: {strOverlaps}");
}
}
if (isSP4Stable && isSP2STable)
{
break;
}
}
}
}
//
// SP+TM at L2
for (int i = 0; i < maxCycles; i++)
{
matches = 0;
cycle = i;
Debug.WriteLine($"-------------- L2 TM Train region Cycle {cycle} ---------------");
foreach (double input in inputs)
{
Debug.WriteLine($"-------------- {input} ---------------");
// Reset tha array
//var cellSdrL4Indexes = L4_ActiveCell_sdr_log[input];
object layerL4Out = layerL4.Compute(input, learn);
previousInputs.Add(input.ToString());
if (previousInputs.Count > (maxPrevInputs + 1))
{
previousInputs.RemoveAt(0);
}
if (previousInputs.Count < maxPrevInputs)
{
continue;
}
key = GetKey(previousInputs, input);
List <Cell> actCells;
InitArray(inpCellsL4ToL2, 0);
int[] cellSdrL4Indexes;
if (!isSimilar_L4_active_cell_sdr)
{
cellSdrL4Indexes = L4_ActiveCell_sdr_log[input];
}
else
{
cellSdrL4Indexes = memL4.ActiveCells.Select(c => c.Index).ToArray();
}
// Set the output active cell array
ArrayUtils.SetIndexesTo(inpCellsL4ToL2, cellSdrL4Indexes, 1);
ComputeCycle layerL2Out = layerL2.Compute(inpCellsL4ToL2, true) as ComputeCycle;
if (layerL2Out.ActiveCells.Count == layerL2Out.WinnerCells.Count)
{
actCells = layerL2Out.ActiveCells;
}
else
{
actCells = layerL2Out.WinnerCells;
}
/// <summary>
/// HTM Classifier has added for Layer 2
/// </summary>
cls.Learn(key, actCells.ToArray());
if (key == lastPredictedValue)
{
matches++;
Debug.WriteLine($"Match. Actual Sequence: {key} - Last Predicted Sequence: {lastPredictedValue}");
}
else
{
Debug.WriteLine($"Missmatch! Actual Sequence: {key} - Last Predicted Sequence: {lastPredictedValue}");
}
/// <summary>
/// Classifier is taking Predictive Cells from Layer 2
/// </summary>
if (layerL2Out.PredictiveCells.Count > 0)
{
string predictedInputValue = cls.GetPredictedInputValue(layerL2Out.PredictiveCells.ToArray());
Debug.WriteLine($"Current Input: {input} \t| New Predicted Input Sequence: {predictedInputValue}");
lastPredictedValue = predictedInputValue;
}
else
{
Debug.WriteLine($"NO CELLS PREDICTED for next cycle.");
lastPredictedValue = String.Empty;
}
}
double accuracy = (double)matches / (double)inputs.Length * 100.0;
Debug.WriteLine($"Cycle: {cycle}\tMatches={matches} of {inputs.Length}\t {accuracy}%");
if (accuracy >= 100.0)
{
maxMatchCnt++;
Debug.WriteLine($"100% accuracy reched {maxMatchCnt} times.");
//
// Experiment is completed if we are 20 cycles long at the 100% accuracy.
if (maxMatchCnt >= 20)
{
Debug.WriteLine($"Exit experiment in the stable state after 20 repeats with 100% of accuracy.");
learn = false;
break;
}
}
else if (maxMatchCnt > 0)
{
Debug.WriteLine($"At 100% accuracy after {maxMatchCnt} repeats we get a drop of accuracy with {accuracy}. This indicates instable state. Learning will be continued.");
}
}
}
/// <summary>
/// Implements the experiment.
/// </summary>
/// <param name="cfg"></param>
/// <param name="encoder"></param>
/// <param name="inputValues"></param>
private static void RunExperiment(HtmConfig cfg, EncoderBase encoder, List <double> inputValues)
{
// Creates the htm memory.
var mem = new Connections(cfg);
bool isInStableState = false;
//
// HPC extends the default Spatial Pooler algorithm.
// The purpose of HPC is to set the SP in the new-born stage at the begining of the learning process.
// In this stage the boosting is very active, but the SP behaves instable. After this stage is over
// (defined by the second argument) the HPC is controlling the learning process of the SP.
// Once the SDR generated for every input gets stable, the HPC will fire event that notifies your code
// that SP is stable now.
HomeostaticPlasticityController hpa = new HomeostaticPlasticityController(mem, inputValues.Count * 15,
(isStable, numPatterns, actColAvg, seenInputs) =>
{
// Event should only be fired when entering the stable state.
// Ideal SP should never enter unstable state after stable state.
if (isStable == false)
{
Debug.WriteLine($"INSTABLE");
// This should usually not happen.
isInStableState = false;
}
else
{
Debug.WriteLine($"STABILITY");
// Here you can perform any action if required.
isInStableState = true;
}
});
// It creates the instance of Spatial Pooler Multithreaded version.
SpatialPooler sp = new SpatialPoolerMT(hpa);
// Initializes the
sp.Init(mem, new DistributedMemory()
{
ColumnDictionary = new InMemoryDistributedDictionary <int, NeoCortexApi.Entities.Column>(1)
});
// It creates the instance of the neo-cortex layer.
// Algorithm will be performed inside of that layer.
CortexLayer <object, object> cortexLayer = new CortexLayer <object, object>("L1");
// Add encoder as the very first module. This model is connected to the sensory input cells
// that receive the input. Encoder will receive the input and forward the encoded signal
// to the next module.
cortexLayer.HtmModules.Add("encoder", encoder);
// The next module in the layer is Spatial Pooler. This module will receive the output of the
// encoder.
cortexLayer.HtmModules.Add("sp", sp);
double[] inputs = inputValues.ToArray();
// Will hold the SDR of every inputs.
Dictionary <double, int[]> prevActiveCols = new Dictionary <double, int[]>();
// Will hold the similarity of SDKk and SDRk-1 fro every input.
Dictionary <double, double> prevSimilarity = new Dictionary <double, double>();
//
// Initiaize start similarity to zero.
foreach (var input in inputs)
{
prevSimilarity.Add(input, 0.0);
prevActiveCols.Add(input, new int[0]);
}
// Learning process will take 1000 iterations (cycles)
int maxSPLearningCycles = 1000;
for (int cycle = 0; cycle < maxSPLearningCycles; cycle++)
{
Debug.WriteLine($"Cycle ** {cycle} ** Stability: {isInStableState}");
//
// This trains the layer on input pattern.
foreach (var input in inputs)
{
double similarity;
// Learn the input pattern.
// Output lyrOut is the output of the last module in the layer.
//
var lyrOut = cortexLayer.Compute((object)input, true) as int[];
// This is a general way to get the SpatialPooler result from the layer.
var activeColumns = cortexLayer.GetResult("sp") as int[];
var actCols = activeColumns.OrderBy(c => c).ToArray();
similarity = MathHelpers.CalcArraySimilarity(activeColumns, prevActiveCols[input]);
Debug.WriteLine($"[cycle={cycle.ToString("D4")}, i={input}, cols=:{actCols.Length} s={similarity}] SDR: {Helpers.StringifyVector(actCols)}");
prevActiveCols[input] = activeColumns;
prevSimilarity[input] = similarity;
}
}
}
public void TestCortexLayer()
{
int inputBits = 100;
double max = 20;
int numColumns = 2048;
List <double> inputValues = new List <double>(new double[] { 0.0, 1.0, 0.0, 2.0, 3.0, 4.0, 5.0, 6.0, 5.0, 4.0, 3.0, 7.0, 1.0, 9.0, 12.0, 11.0, 12.0, 13.0, 14.0, 11.0, 12.0, 14.0, 5.0, 7.0, 6.0, 9.0, 3.0, 4.0, 3.0, 4.0, 3.0, 4.0 });
int numInputs = inputValues.Distinct().ToList().Count;
var inputs = inputValues.ToArray();
Dictionary <string, object> settings = new Dictionary <string, object>()
{
{ "W", 15 },
{ "N", inputBits },
{ "Radius", -1.0 },
{ "MinVal", 0.0 },
{ "Periodic", false },
{ "Name", "scalar" },
{ "ClipInput", false },
{ "MaxVal", max }
};
EncoderBase encoder = new ScalarEncoder(settings);
HtmConfig htmConfig = new HtmConfig(new int[] { inputBits }, new int[] { numColumns })
{
Random = new ThreadSafeRandom(42),
CellsPerColumn = 25,
GlobalInhibition = true,
LocalAreaDensity = -1,
NumActiveColumnsPerInhArea = 0.02 * numColumns,
PotentialRadius = 50,
InhibitionRadius = 15,
MaxBoost = 10.0,
DutyCyclePeriod = 25,
MinPctOverlapDutyCycles = 0.75,
MaxNewSynapseCount = (int)(0.02 * numColumns),
ActivationThreshold = 15,
ConnectedPermanence = 0.5,
PermanenceDecrement = 0.25,
PermanenceIncrement = 0.15,
PredictedSegmentDecrement = 0.1
};
Connections memory = new Connections(htmConfig);
HomeostaticPlasticityController hpa = new HomeostaticPlasticityController(memory, numInputs * 55, (isStable, numPatterns, actColAvg, seenInputs) =>
{
if (isStable)
{
// Event should be fired when entering the stable state.
Debug.WriteLine($"STABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
else
{
// Ideal SP should never enter unstable state after stable state.
Debug.WriteLine($"INSTABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
}, numOfCyclesToWaitOnChange: 25);
SpatialPoolerMT spatialPooler = new SpatialPoolerMT(hpa);
spatialPooler.Init(memory, UnitTestHelpers.GetMemory());
TemporalMemory temporalMemory = new TemporalMemory();
temporalMemory.Init(memory);
List <CortexRegion> regions = new List <CortexRegion>();
CortexRegion region0 = new CortexRegion("1st Region");
regions.Add(region0);
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
region0.AddLayer(layer1);
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", spatialPooler);
layer1.HtmModules.Add("tm", temporalMemory);
bool learn = true;
int maxCycles = 3500;
for (int i = 0; i < maxCycles; i++)
{
foreach (var input in inputs)
{
var lyrOut = layer1.Compute(input, learn) as ComputeCycle;
}
}
}
public void LongerSequenceExperiment()
{
int inputBits = 1024;
bool learn = true;
Parameters p = Parameters.getAllDefaultParameters();
p.Set(KEY.RANDOM, new ThreadSafeRandom(42));
p.Set(KEY.INPUT_DIMENSIONS, new int[] { inputBits });
p.Set(KEY.CELLS_PER_COLUMN, 10);
p.Set(KEY.COLUMN_DIMENSIONS, new int[] { 2048 });
CortexNetwork net = new CortexNetwork("my cortex");
List <CortexRegion> regions = new List <CortexRegion>();
CortexRegion region0 = new CortexRegion("1st Region");
regions.Add(region0);
SpatialPoolerMT sp1 = new SpatialPoolerMT();
TemporalMemory tm1 = new TemporalMemory();
var mem = new Connections();
p.apply(mem);
sp1.Init(mem, UnitTestHelpers.GetMemory());
tm1.Init(mem);
Dictionary <string, object> settings = new Dictionary <string, object>()
{
{ "W", 21 },
{ "N", inputBits },
{ "Radius", -1.0 },
{ "MinVal", 0.0 },
// { "MaxVal", 20.0 },
{ "Periodic", false },
{ "Name", "scalar" },
{ "ClipInput", false },
};
double max = 50;
List <double> lst = new List <double>();
for (double i = 0; i < max; i++)
{
lst.Add(i);
}
settings["MaxVal"] = max;
EncoderBase encoder = new ScalarEncoder(settings);
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
//
// NewBorn learning stage.
region0.AddLayer(layer1);
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp1);
HtmClassifier <double, ComputeCycle> cls = new HtmClassifier <double, ComputeCycle>();
double[] inputs = lst.ToArray();
//
// This trains SP.
foreach (var input in inputs)
{
Debug.WriteLine($" ** {input} **");
for (int i = 0; i < 3; i++)
{
var lyrOut = layer1.Compute((object)input, learn) as ComputeCycle;
}
}
// Here we add TM module to the layer.
layer1.HtmModules.Add("tm", tm1);
//
// Now, training with SP+TM. SP is pretrained on pattern.
for (int i = 0; i < 200; i++)
{
foreach (var input in inputs)
{
var lyrOut = layer1.Compute(input, learn) as ComputeCycle;
cls.Learn(input, lyrOut.ActiveCells.ToArray());
Debug.WriteLine($"-------------- {input} ---------------");
if (learn == false)
{
Debug.WriteLine($"Inference mode");
}
Debug.WriteLine($"W: {Helpers.StringifyVector(lyrOut.WinnerCells.Select(c => c.Index).ToArray())}");
Debug.WriteLine($"P: {Helpers.StringifyVector(lyrOut.PredictiveCells.Select(c => c.Index).ToArray())}");
Debug.WriteLine($"Current Input: {input} \t| Predicted Input: {cls.GetPredictedInputValue(lyrOut.PredictiveCells.ToArray())}");
}
if (i == 50)
{
Debug.WriteLine("Stop Learning From Here. Entering inference mode.");
learn = false;
}
tm1.Reset(mem);
}
cls.TraceState();
Debug.WriteLine("------------------------------------------------------------------------\n----------------------------------------------------------------------------");
}
public void RunPowerPredictionExperiment()
{
const int inputBits = 300; /* without datetime component */ // 13420; /* with 4096 scalar bits */ // 10404 /* with 1024 bits */;
Parameters p = Parameters.getAllDefaultParameters();
p.Set(KEY.RANDOM, new ThreadSafeRandom(42));
p.Set(KEY.COLUMN_DIMENSIONS, new int[] { 2048 });
p.Set(KEY.INPUT_DIMENSIONS, new int[] { inputBits });
p.Set(KEY.CELLS_PER_COLUMN, 10 /* 50 */);
p.Set(KEY.GLOBAL_INHIBITION, true);
p.Set(KEY.CONNECTED_PERMANENCE, 0.1);
// N of 40 (40= 0.02*2048 columns) active cells required to activate the segment.
p.setNumActiveColumnsPerInhArea(0.02 * 2048);
// Activation threshold is 10 active cells of 40 cells in inhibition area.
p.setActivationThreshold(10 /*15*/);
p.setInhibitionRadius(15);
p.Set(KEY.MAX_BOOST, 0.0);
p.Set(KEY.DUTY_CYCLE_PERIOD, 100000);
p.setActivationThreshold(10);
p.setMaxNewSynapsesPerSegmentCount((int)(0.02 * 2048));
p.setPermanenceIncrement(0.17);
//p.Set(KEY.MAX_SYNAPSES_PER_SEGMENT, 32);
//p.Set(KEY.MAX_SEGMENTS_PER_CELL, 128);
//p.Set(KEY.MAX_NEW_SYNAPSE_COUNT, 200);
//p.Set(KEY.POTENTIAL_RADIUS, 700);
//p.Set(KEY.POTENTIAL_PCT, 0.5);
//p.Set(KEY.NUM_ACTIVE_COLUMNS_PER_INH_AREA, 42);
//p.Set(KEY.LOCAL_AREA_DENSITY, -1);
CortexRegion region0 = new CortexRegion("1st Region");
SpatialPoolerMT sp1 = new SpatialPoolerMT();
TemporalMemory tm1 = new TemporalMemory();
var mem = new Connections();
p.apply(mem);
sp1.Init(mem, UnitTestHelpers.GetMemory());
tm1.Init(mem);
Dictionary <string, object> settings = new Dictionary <string, object>();
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
region0.AddLayer(layer1);
layer1.HtmModules.Add("sp", sp1);
HtmClassifier <double, ComputeCycle> cls = new HtmClassifier <double, ComputeCycle>();
Stopwatch sw = new Stopwatch();
sw.Start();
Train(inputBits, layer1, cls, true); // New born mode.
sw.Stop();
Debug.WriteLine($"NewBorn stage duration: {sw.ElapsedMilliseconds / 1000} s");
layer1.AddModule("tm", tm1);
sw.Start();
int hunderdAccCnt = 0;
for (int i = 0; i < 1000; i++)
{
float acc = Train(inputBits, layer1, cls, false);
Debug.WriteLine($"Accuracy = {acc}, Cycle = {i}");
if (acc == 100.0)
{
hunderdAccCnt++;
}
if (hunderdAccCnt >= 10)
{
break;
}
//tm1.reset(mem);
}
if (hunderdAccCnt >= 10)
{
Debug.WriteLine($"EXPERIMENT SUCCESS. Accurracy 100% reached.");
}
else
{
Debug.WriteLine($"Experiment FAILED!. Accurracy 100% was not reached.");
}
cls.TraceState();
sw.Stop();
Debug.WriteLine($"Training duration: {sw.ElapsedMilliseconds / 1000} s");
}
/// <summary>
///
/// </summary>
private HtmPredictionEngine RunExperiment(int inputBits, HtmConfig cfg, EncoderBase encoder, Dictionary <string, List <double> > sequences)
{
Stopwatch sw = new Stopwatch();
sw.Start();
int maxMatchCnt = 0;
var mem = new Connections(cfg);
bool isInStableState = false;
HtmClassifier <string, ComputeCycle> cls = new HtmClassifier <string, ComputeCycle>();
var numUniqueInputs = GetNumberOfInputs(sequences);
CortexLayer <object, object> layer1 = new CortexLayer <object, object>("L1");
TemporalMemory tm = new TemporalMemory();
// For more information see following paper: https://www.scitepress.org/Papers/2021/103142/103142.pdf
HomeostaticPlasticityController hpc = new HomeostaticPlasticityController(mem, numUniqueInputs * 150, (isStable, numPatterns, actColAvg, seenInputs) =>
{
if (isStable)
{
// Event should be fired when entering the stable state.
Debug.WriteLine($"STABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
else
{
// Ideal SP should never enter unstable state after stable state.
Debug.WriteLine($"INSTABLE: Patterns: {numPatterns}, Inputs: {seenInputs}, iteration: {seenInputs / numPatterns}");
}
// We are not learning in instable state.
isInStableState = isStable;
// Clear active and predictive cells.
//tm.Reset(mem);
}, numOfCyclesToWaitOnChange: 50);
SpatialPoolerMT sp = new SpatialPoolerMT(hpc);
sp.Init(mem);
tm.Init(mem);
// Please note that we do not add here TM in the layer.
// This is omitted for practical reasons, because we first eneter the newborn-stage of the algorithm
// In this stage we want that SP get boosted and see all elements before we start learning with TM.
// All would also work fine with TM in layer, but it would work much slower.
// So, to improve the speed of experiment, we first ommit the TM and then after the newborn-stage we add it to the layer.
layer1.HtmModules.Add("encoder", encoder);
layer1.HtmModules.Add("sp", sp);
//double[] inputs = inputValues.ToArray();
int[] prevActiveCols = new int[0];
int cycle = 0;
int matches = 0;
var lastPredictedValues = new List <string>(new string[] { "0" });
int maxCycles = 3500;
//
// Training SP to get stable. New-born stage.
//
for (int i = 0; i < maxCycles && isInStableState == false; i++)
{
matches = 0;
cycle++;
Debug.WriteLine($"-------------- Newborn Cycle {cycle} ---------------");
foreach (var inputs in sequences)
{
foreach (var input in inputs.Value)
{
Debug.WriteLine($" -- {inputs.Key} - {input} --");
var lyrOut = layer1.Compute(input, true);
if (isInStableState)
{
break;
}
}
if (isInStableState)
{
break;
}
}
}
// Clear all learned patterns in the classifier.
cls.ClearState();
// We activate here the Temporal Memory algorithm.
layer1.HtmModules.Add("tm", tm);
//
// Loop over all sequences.
foreach (var sequenceKeyPair in sequences)
{
Debug.WriteLine($"-------------- Sequences {sequenceKeyPair.Key} ---------------");
int maxPrevInputs = sequenceKeyPair.Value.Count - 1;
List <string> previousInputs = new List <string>();
previousInputs.Add("-1.0");
//
// Now training with SP+TM. SP is pretrained on the given input pattern set.
for (int i = 0; i < maxCycles; i++)
{
matches = 0;
cycle++;
Debug.WriteLine("");
Debug.WriteLine($"-------------- Cycle {cycle} ---------------");
Debug.WriteLine("");
foreach (var input in sequenceKeyPair.Value)
{
Debug.WriteLine($"-------------- {input} ---------------");
var lyrOut = layer1.Compute(input, true) as ComputeCycle;
var activeColumns = layer1.GetResult("sp") as int[];
previousInputs.Add(input.ToString());
if (previousInputs.Count > (maxPrevInputs + 1))
{
previousInputs.RemoveAt(0);
}
// In the pretrained SP with HPC, the TM will quickly learn cells for patterns
// In that case the starting sequence 4-5-6 might have the sam SDR as 1-2-3-4-5-6,
// Which will result in returning of 4-5-6 instead of 1-2-3-4-5-6.
// HtmClassifier allways return the first matching sequence. Because 4-5-6 will be as first
// memorized, it will match as the first one.
if (previousInputs.Count < maxPrevInputs)
{
continue;
}
string key = GetKey(previousInputs, input, sequenceKeyPair.Key);
List <Cell> actCells;
if (lyrOut.ActiveCells.Count == lyrOut.WinnerCells.Count)
{
actCells = lyrOut.ActiveCells;
}
else
{
actCells = lyrOut.WinnerCells;
}
cls.Learn(key, actCells.ToArray());
Debug.WriteLine($"Col SDR: {Helpers.StringifyVector(lyrOut.ActivColumnIndicies)}");
Debug.WriteLine($"Cell SDR: {Helpers.StringifyVector(actCells.Select(c => c.Index).ToArray())}");
//
// If the list of predicted values from the previous step contains the currently presenting value,
// we have a match.
if (lastPredictedValues.Contains(key))
{
matches++;
Debug.WriteLine($"Match. Actual value: {key} - Predicted value: {lastPredictedValues.FirstOrDefault(key)}.");
}
else
{
Debug.WriteLine($"Missmatch! Actual value: {key} - Predicted values: {String.Join(',', lastPredictedValues)}");
}
if (lyrOut.PredictiveCells.Count > 0)
{
//var predictedInputValue = cls.GetPredictedInputValue(lyrOut.PredictiveCells.ToArray());
var predictedInputValues = cls.GetPredictedInputValues(lyrOut.PredictiveCells.ToArray(), 3);
foreach (var item in predictedInputValues)
{
Debug.WriteLine($"Current Input: {input} \t| Predicted Input: {item.PredictedInput} - {item.Similarity}");
}
lastPredictedValues = predictedInputValues.Select(v => v.PredictedInput).ToList();
}
else
{
Debug.WriteLine($"NO CELLS PREDICTED for next cycle.");
lastPredictedValues = new List <string> ();
}
}
// The first element (a single element) in the sequence cannot be predicted
double maxPossibleAccuraccy = (double)((double)sequenceKeyPair.Value.Count - 1) / (double)sequenceKeyPair.Value.Count * 100.0;
double accuracy = (double)matches / (double)sequenceKeyPair.Value.Count * 100.0;
Debug.WriteLine($"Cycle: {cycle}\tMatches={matches} of {sequenceKeyPair.Value.Count}\t {accuracy}%");
if (accuracy >= maxPossibleAccuraccy)
{
maxMatchCnt++;
Debug.WriteLine($"100% accuracy reched {maxMatchCnt} times.");
//
// Experiment is completed if we are 30 cycles long at the 100% accuracy.
if (maxMatchCnt >= 30)
{
sw.Stop();
Debug.WriteLine($"Sequence learned. The algorithm is in the stable state after 30 repeats with with accuracy {accuracy} of maximum possible {maxMatchCnt}. Elapsed sequence {sequenceKeyPair.Key} learning time: {sw.Elapsed}.");
break;
}
}
else if (maxMatchCnt > 0)
{
Debug.WriteLine($"At 100% accuracy after {maxMatchCnt} repeats we get a drop of accuracy with accuracy {accuracy}. This indicates instable state. Learning will be continued.");
maxMatchCnt = 0;
}
// This resets the learned state, so the first element starts allways from the beginning.
tm.Reset(mem);
}
}
Debug.WriteLine("------------ END ------------");
return(new HtmPredictionEngine {
Layer = layer1, Classifier = cls, Connections = mem
});
}
