public void TestReinforcedSelectedMatchingSegmentInBurstingColumn()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = getDefaultParameters(null, KEY.PERMANENCE_DECREMENT, 0.08);
p.apply(cn);
tm.Init(cn);
int[] previousActiveColumns = { 0 };
int[] activeColumns = { 1 };
Cell[] previousActiveCells = { cn.GetCell(0), cn.GetCell(1), cn.GetCell(2), cn.GetCell(3) };
Cell[] burstingCells = { cn.GetCell(4), cn.GetCell(5) };
DistalDendrite activeSegment = cn.CreateDistalSegment(burstingCells[0]);
Synapse as1 = cn.CreateSynapse(activeSegment, previousActiveCells[0], 0.3);
Synapse as2 = cn.CreateSynapse(activeSegment, previousActiveCells[0], 0.3);
Synapse as3 = cn.CreateSynapse(activeSegment, previousActiveCells[0], 0.3);
Synapse is1 = cn.CreateSynapse(activeSegment, cn.GetCell(81), 0.3);
DistalDendrite otherMatchingSegment = cn.CreateDistalSegment(burstingCells[1]);
cn.CreateSynapse(otherMatchingSegment, previousActiveCells[0], 0.3);
cn.CreateSynapse(otherMatchingSegment, previousActiveCells[1], 0.3);
cn.CreateSynapse(otherMatchingSegment, cn.GetCell(81), 0.3);
tm.Compute(previousActiveColumns, true);
tm.Compute(activeColumns, true);
Assert.AreEqual(0.4, as1.Permanence, 0.01);
Assert.AreEqual(0.4, as2.Permanence, 0.01);
Assert.AreEqual(0.4, as3.Permanence, 0.01);
Assert.AreEqual(0.22, is1.Permanence, 0.001);
}
public void TestObjectGroup()
{
Column c0 = new Column(9, 0);
Column c1 = new Column(9, 1);
// Illustrates the Cell's actual index = colIndex * cellsPerColumn + indexOfCellWithinCol
Assert.AreEqual(7, c0.GetCell(7).GetIndex());
Assert.AreEqual(12, c1.GetCell(3).GetIndex());
Assert.AreEqual(16, c1.GetCell(7).GetIndex());
DistalDendrite dd0 = new DistalDendrite(c0.GetCell(7), 0, 0, 0);
DistalDendrite dd1 = new DistalDendrite(c1.GetCell(3 /* Col 1's Cells start at 9 */), 1, 0, 1);
DistalDendrite dd2 = new DistalDendrite(c1.GetCell(7 /* Col 1's Cells start at 9 */), 2, 0, 2);
List <DistalDendrite> l = new List <DistalDendrite> {
dd0, dd1, dd2
};
//@SuppressWarnings("unchecked")
List <Tuple <DistalDendrite, Column> > expected = new List <Tuple <DistalDendrite, Column> >
{
new Tuple <DistalDendrite, Column>(dd0, c0),
new Tuple <DistalDendrite, Column>(dd1, c1),
new Tuple <DistalDendrite, Column>(dd2, c1)
};
GroupBy <DistalDendrite, Column> grouper = GroupBy <DistalDendrite, Column> .Of(l, d => d.GetParentCell().GetColumn());
int i = 0;
foreach (Tuple <DistalDendrite, Column> p in grouper)
{
Assert.AreEqual(expected[i++], p);
}
}
public void TestColumnSerialize()
{
//Thread.Sleep(5000);
//Pool pool = new Pool(10, 10);
Cell cell = new Cell();
DistalDendrite dist = new DistalDendrite(cell, 0, 0, 0, 0.5, 10);
dist.Synapses.Add(new Synapse(cell, null, 0, 0.5));
Synapse syn = new Synapse(cell, dist, 0, 0);
var dict = UnitTestHelpers.GetMemory();
Column col = new Column(10, 0, 0.01, 10);
col.ProximalDendrite = new ProximalDendrite(0, 0.01, 10);
col.ProximalDendrite.Synapses = new List <Synapse>();
col.ProximalDendrite.Synapses.Add(syn);
dict.ColumnDictionary.Add(0, col);
var serCol = AkkaSb.Net.ActorReference.SerializeMsg(col);
Assert.IsTrue(dict.ColumnDictionary[0].ProximalDendrite.Synapses[0].Segment != null);
}
public void testDestroyWeakSynapseOnActiveReinforce()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = GetDefaultParameters(null, Parameters.KEY.INITIAL_PERMANENCE, 0.2);
p = GetDefaultParameters(p, Parameters.KEY.MAX_NEW_SYNAPSE_COUNT, 4);
p = GetDefaultParameters(p, Parameters.KEY.PREDICTED_SEGMENT_DECREMENT, 0.02);
p.Apply(cn);
TemporalMemory.Init(cn);
int[] previousActiveColumns = { 0 };
Cell[] previousActiveCells = { cn.GetCell(0), cn.GetCell(1), cn.GetCell(2), cn.GetCell(3) };
int[] activeColumns = { 2 };
Cell expectedActiveCell = cn.GetCell(5);
DistalDendrite activeSegment = cn.CreateSegment(expectedActiveCell);
cn.CreateSynapse(activeSegment, previousActiveCells[0], 0.5);
cn.CreateSynapse(activeSegment, previousActiveCells[1], 0.5);
cn.CreateSynapse(activeSegment, previousActiveCells[2], 0.5);
// Weak Synapse
cn.CreateSynapse(activeSegment, previousActiveCells[3], 0.009);
tm.Compute(cn, previousActiveColumns, true);
tm.Compute(cn, activeColumns, true);
Assert.AreEqual(3, cn.GetNumSynapses(activeSegment));
}
public void testZeroActiveColumns()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = GetDefaultParameters();
p.Apply(cn);
TemporalMemory.Init(cn);
int[] previousActiveColumns = { 0 };
Cell cell4 = cn.GetCell(4);
DistalDendrite activeSegment = cn.CreateSegment(cell4);
cn.CreateSynapse(activeSegment, cn.GetCell(0), 0.5);
cn.CreateSynapse(activeSegment, cn.GetCell(1), 0.5);
cn.CreateSynapse(activeSegment, cn.GetCell(2), 0.5);
cn.CreateSynapse(activeSegment, cn.GetCell(3), 0.5);
ComputeCycle cc = tm.Compute(cn, previousActiveColumns, true);
Assert.IsFalse(cc.ActiveCells().Count == 0);
Assert.IsFalse(cc.WinnerCells().Count == 0);
Assert.IsFalse(cc.PredictiveCells().Count == 0);
int[] zeroColumns = new int[0];
ComputeCycle cc2 = tm.Compute(cn, zeroColumns, true);
Assert.IsTrue(cc2.ActiveCells().Count == 0);
Assert.IsTrue(cc2.WinnerCells().Count == 0);
Assert.IsTrue(cc2.PredictiveCells().Count == 0);
}
public void testNoChangeToNonSelectedMatchingSegmentsInBurstingColumn()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = GetDefaultParameters(null, Parameters.KEY.PERMANENCE_DECREMENT, 0.08);
p.Apply(cn);
TemporalMemory.Init(cn);
int[] previousActiveColumns = { 0 };
int[] activeColumns = { 1 };
Cell[] previousActiveCells = { cn.GetCell(0), cn.GetCell(1), cn.GetCell(2), cn.GetCell(3) };
Cell[] burstingCells = { cn.GetCell(4), cn.GetCell(5) };
DistalDendrite selectedMatchingSegment = cn.CreateSegment(burstingCells[0]);
cn.CreateSynapse(selectedMatchingSegment, previousActiveCells[0], 0.3);
cn.CreateSynapse(selectedMatchingSegment, previousActiveCells[1], 0.3);
cn.CreateSynapse(selectedMatchingSegment, previousActiveCells[2], 0.3);
cn.CreateSynapse(selectedMatchingSegment, cn.GetCell(81), 0.3);
DistalDendrite otherMatchingSegment = cn.CreateSegment(burstingCells[1]);
Synapse as1 = cn.CreateSynapse(otherMatchingSegment, previousActiveCells[0], 0.3);
Synapse as2 = cn.CreateSynapse(otherMatchingSegment, previousActiveCells[1], 0.3);
Synapse is1 = cn.CreateSynapse(otherMatchingSegment, cn.GetCell(81), 0.3);
tm.Compute(cn, previousActiveColumns, true);
tm.Compute(cn, activeColumns, true);
Assert.AreEqual(0.3, as1.GetPermanence(), 0.01);
Assert.AreEqual(0.3, as2.GetPermanence(), 0.01);
Assert.AreEqual(0.3, is1.GetPermanence(), 0.01);
}
/**
* Creates nDesiredNewSynapes synapses on the segment passed in if
* possible, choosing random cells from the previous winner cells that are
* not already on the segment.
* <p>
* <b>Notes:</b> The process of writing the last value into the index in the array
* that was most recently changed is to ensure the same results that we get
* in the c++ implementation using iter_swap with vectors.
* </p>
*
* @param conn Connections instance for the tm
* @param prevWinnerCells Winner cells in `t-1`
* @param segment Segment to grow synapses on.
* @param initialPermanence Initial permanence of a new synapse.
* @param nDesiredNewSynapses Desired number of synapses to grow
* @param random Tm object used to generate random
* numbers
*/
public void GrowSynapses(Connections conn, HashSet <Cell> prevWinnerCells, DistalDendrite segment,
double initialPermanence, int nDesiredNewSynapses, IRandom random)
{
List <Cell> candidates = new List <Cell>(prevWinnerCells);
candidates.Sort();
//Collections.sort(candidates);
foreach (Synapse synapse in conn.GetSynapses(segment))
{
Cell presynapticCell = synapse.GetPresynapticCell();
int index = candidates.IndexOf(presynapticCell);
if (index != -1)
{
candidates.RemoveAt(index);
}
}
int candidatesLength = candidates.Count;
int nActual = nDesiredNewSynapses < candidatesLength ? nDesiredNewSynapses : candidatesLength;
for (int i = 0; i < nActual; i++)
{
int rand = random.NextInt(candidates.Count);
conn.CreateSynapse(segment, candidates[rand], initialPermanence);
candidates.RemoveAt(rand);
}
}
public void testPredictedActiveCellsAreAlwaysWinners()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = GetDefaultParameters();
p.Apply(cn);
TemporalMemory.Init(cn);
int[] previousActiveColumns = { 0 };
int[] activeColumns = { 1 };
Cell[] previousActiveCells = { cn.GetCell(0), cn.GetCell(1), cn.GetCell(2), cn.GetCell(3) };
List <Cell> expectedWinnerCells = new List <Cell>(cn.GetCellSet(new int[] { 4, 6 }));
DistalDendrite activeSegment1 = cn.CreateSegment(expectedWinnerCells[0]);
cn.CreateSynapse(activeSegment1, previousActiveCells[0], 0.5);
cn.CreateSynapse(activeSegment1, previousActiveCells[1], 0.5);
cn.CreateSynapse(activeSegment1, previousActiveCells[2], 0.5);
DistalDendrite activeSegment2 = cn.CreateSegment(expectedWinnerCells[1]);
cn.CreateSynapse(activeSegment2, previousActiveCells[0], 0.5);
cn.CreateSynapse(activeSegment2, previousActiveCells[1], 0.5);
cn.CreateSynapse(activeSegment2, previousActiveCells[2], 0.5);
ComputeCycle cc = tm.Compute(cn, previousActiveColumns, false); // learn=false
cc = tm.Compute(cn, activeColumns, false); // learn=false
Assert.IsTrue(cc.winnerCells.SetEquals(new HashSet <Cell>(expectedWinnerCells)));
}
public void TestActivateCorrectlyPredictiveCells()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = GetDefaultParameters();
p.Apply(cn);
TemporalMemory.Init(cn);
int[] previousActiveColumns = { 0 };
int[] activeColumns = { 1 };
Cell cell4 = cn.GetCell(4);
HashSet <Cell> expectedActiveCells = new HashSet <Cell> {
cell4
}; //Stream.of(cell4).collect(Collectors.toSet());
DistalDendrite activeSegment = cn.CreateSegment(cell4);
cn.CreateSynapse(activeSegment, cn.GetCell(0), 0.5);
cn.CreateSynapse(activeSegment, cn.GetCell(1), 0.5);
cn.CreateSynapse(activeSegment, cn.GetCell(2), 0.5);
cn.CreateSynapse(activeSegment, cn.GetCell(3), 0.5);
ComputeCycle cc = tm.Compute(cn, previousActiveColumns, true);
Assert.IsTrue(cc.PredictiveCells().SetEquals(expectedActiveCells));
ComputeCycle cc2 = tm.Compute(cn, activeColumns, true);
Assert.IsTrue(cc2.ActiveCells().SetEquals(expectedActiveCells));
}
public void SerializeConnectionsTest()
{
int[] inputDims = { 3, 4, 5 };
int[] columnDims = { 35, 43, 52 };
HtmConfig cfg = new HtmConfig(inputDims, columnDims);
Connections connections = new Connections(cfg);
Cell cells = new Cell(12, 14, 16, 18, new CellActivity());
var distSeg1 = new DistalDendrite(cells, 1, 2, 2, 1.0, 100);
var distSeg2 = new DistalDendrite(cells, 44, 24, 34, 1.0, 100);
connections.ActiveSegments.Add(distSeg1);
using (StreamWriter sw = new StreamWriter($"ser_{nameof(SerializeConnectionsTest)}.txt"))
{
connections.Serialize(sw);
}
using (StreamReader sr = new StreamReader($"ser_{nameof(SerializeConnectionsTest)}.txt"))
{
Connections connections1 = Connections.Deserialize(sr);
Assert.IsTrue(connections.Equals(connections1));
}
}
public void testDestroySegmentsWithTooFewSynapsesToBeMatching()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = GetDefaultParameters(null, Parameters.KEY.INITIAL_PERMANENCE, .2);
p = GetDefaultParameters(p, Parameters.KEY.MAX_NEW_SYNAPSE_COUNT, 4);
p = GetDefaultParameters(p, Parameters.KEY.PREDICTED_SEGMENT_DECREMENT, 0.02);
p.Apply(cn);
TemporalMemory.Init(cn);
int[] prevActiveColumns = { 0 };
Cell[] prevActiveCells = { cn.GetCell(0), cn.GetCell(1), cn.GetCell(2), cn.GetCell(3) };
int[] activeColumns = { 2 };
Cell expectedActiveCell = cn.GetCell(5);
DistalDendrite matchingSegment = cn.CreateSegment(cn.GetCell(5));
cn.CreateSynapse(matchingSegment, prevActiveCells[0], .015);
cn.CreateSynapse(matchingSegment, prevActiveCells[1], .015);
cn.CreateSynapse(matchingSegment, prevActiveCells[2], .015);
cn.CreateSynapse(matchingSegment, prevActiveCells[3], .015);
tm.Compute(cn, prevActiveColumns, true);
tm.Compute(cn, activeColumns, true);
Assert.AreEqual(0, cn.GetNumSegments(expectedActiveCell));
}
public void SerializeDistalDendriteList()
{
HtmSerializer2 htm = new HtmSerializer2();
Cell cell = new Cell(1, 1, 1, 1, new CellActivity());
List <DistalDendrite> distals = new List <DistalDendrite>();
distals.Add(new DistalDendrite(cell, 1, 2, 2, 1.0, 100));
distals.Add(new DistalDendrite(cell, 44, 24, 34, 1.0, 100));
List <DistalDendrite> distals2 = new List <DistalDendrite>();
distals2.Add(new DistalDendrite(cell, 1, 2, 2, 1.0, 100));
distals2.Add(new DistalDendrite(cell, 44, 24, 34, 1.0, 100));
Assert.IsTrue(distals.SequenceEqual(distals2));
using (StreamWriter sw = new StreamWriter($"ser_{nameof(SerializeDistalDendriteList)}"))
{
htm.SerializeBegin("UnitTest", sw);
htm.SerializeValue(distals, sw);
htm.SerializeEnd("UnitTest", sw);
}
using (StreamReader sr = new StreamReader($"ser_{nameof(SerializeDistalDendriteList)}"))
{
List <DistalDendrite> distals1 = new List <DistalDendrite>();
while (sr.Peek() > 0)
{
string str = sr.ReadLine();
if (str == htm.ReadBegin(nameof(DistalDendrite)))
{
distals1.Add(DistalDendrite.Deserialize(sr));
}
}
}
}
public void testReinforcedCorrectlyActiveSegments()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = GetDefaultParameters(null, Parameters.KEY.INITIAL_PERMANENCE, 0.2);
p = GetDefaultParameters(p, Parameters.KEY.MAX_NEW_SYNAPSE_COUNT, 4);
p = GetDefaultParameters(p, Parameters.KEY.PERMANENCE_DECREMENT, 0.08);
p = GetDefaultParameters(p, Parameters.KEY.PREDICTED_SEGMENT_DECREMENT, 0.02);
p.Apply(cn);
TemporalMemory.Init(cn);
int[] previousActiveColumns = { 0 };
int[] activeColumns = { 1 };
Cell[] previousActiveCells = { cn.GetCell(0), cn.GetCell(1), cn.GetCell(2), cn.GetCell(3) };
Cell activeCell = cn.GetCell(5);
DistalDendrite activeSegment = cn.CreateSegment(activeCell);
Synapse as1 = cn.CreateSynapse(activeSegment, previousActiveCells[0], 0.5);
Synapse as2 = cn.CreateSynapse(activeSegment, previousActiveCells[1], 0.5);
Synapse as3 = cn.CreateSynapse(activeSegment, previousActiveCells[2], 0.5);
Synapse is1 = cn.CreateSynapse(activeSegment, cn.GetCell(81), 0.5);
tm.Compute(cn, previousActiveColumns, true);
tm.Compute(cn, activeColumns, true);
Assert.AreEqual(0.6, as1.GetPermanence(), 0.1);
Assert.AreEqual(0.6, as2.GetPermanence(), 0.1);
Assert.AreEqual(0.6, as3.GetPermanence(), 0.1);
Assert.AreEqual(0.42, is1.GetPermanence(), 0.001);
}
public void testRecycleLeastRecentlyActiveSegmentToMakeRoomForNewSegment()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = getDefaultParameters(null, KEY.CELLS_PER_COLUMN, 1);
p = getDefaultParameters(p, KEY.INITIAL_PERMANENCE, 0.5);
p = getDefaultParameters(p, KEY.PERMANENCE_INCREMENT, 0.02);
p = getDefaultParameters(p, KEY.PERMANENCE_DECREMENT, 0.02);
p.Set(KEY.MAX_SEGMENTS_PER_CELL, 2);
p.apply(cn);
tm.init(cn);
int[] prevActiveColumns1 = { 0, 1, 2 };
int[] prevActiveColumns2 = { 3, 4, 5 };
int[] prevActiveColumns3 = { 6, 7, 8 };
int[] activeColumns = { 9 };
Cell cell9 = cn.getCell(9);
tm.Compute(prevActiveColumns1, true);
tm.Compute(activeColumns, true);
Assert.AreEqual(1, cn.getSegments(cell9).Count);
DistalDendrite oldestSegment = cn.getSegments(cell9)[0];
tm.reset(cn);
tm.Compute(prevActiveColumns2, true);
tm.Compute(activeColumns, true);
Assert.AreEqual(2, cn.getSegments(cell9).Count);
//Set<Cell> oldPresynaptic = cn.getSynapses(oldestSegment)
// .stream()
// .map(s->s.getPresynapticCell())
// .collect(Collectors.toSet());
var oldPresynaptic = cn.getSynapses(oldestSegment).Select(s => s.getPresynapticCell()).ToList();
tm.reset(cn);
tm.Compute(prevActiveColumns3, true);
tm.Compute(activeColumns, true);
Assert.AreEqual(2, cn.getSegments(cell9).Count);
// Verify none of the segments are connected to the cells the old
// segment was connected to.
foreach (DistalDendrite segment in cn.getSegments(cell9))
{
//Set<Cell> newPresynaptic = cn.getSynapses(segment)
// .stream()
// .map(s->s.getPresynapticCell())
// .collect(Collectors.toSet());
var newPresynaptic = cn.getSynapses(segment).Select(s => s.getPresynapticCell()).ToList();
Assert.IsTrue(areDisjoined <Cell>(oldPresynaptic, newPresynaptic));
}
}
/**
* Activates all of the cells in an unpredicted active column,
* chooses a winner cell, and, if learning is turned on, either adapts or
* creates a segment. growSynapses is invoked on this segment.
* </p><p>
* <b>Pseudocode:</b>
* </p><p>
* <pre>
* mark all cells as active
* if there are any matching distal dendrite segments
* find the most active matching segment
* mark its cell as a winner cell
* (learning)
* grow and reinforce synapses to previous winner cells
* else
* find the cell with the least segments, mark it as a winner cell
* (learning)
* (optimization) if there are previous winner cells
* add a segment to this winner cell
* grow synapses to previous winner cells
* </pre>
* </p>
*
* @param conn Connections instance for the TM
* @param column Bursting {@link Column}
* @param matchingSegments List of matching {@link DistalDendrite}s
* @param prevActiveCells Active cells in `t-1`
* @param prevWinnerCells Winner cells in `t-1`
* @param permanenceIncrement Amount by which permanences of synapses
* are decremented during learning
* @param permanenceDecrement Amount by which permanences of synapses
* are incremented during learning
* @param random Random number generator
* @param learn Whether or not learning is enabled
*
* @return Tuple containing:
* cells list of the processed column's cells
* bestCell the best cell
*/
public BurstingResult BurstColumn(Connections conn, Column column, List <DistalDendrite> matchingSegments,
ICollection <Cell> prevActiveCells, ICollection <Cell> prevWinnerCells, double permanenceIncrement, double permanenceDecrement,
Random random, bool learn)
{
IList <Cell> cells = column.Cells;
Cell leastUsedCell = null;
//
// Matching segments result from number of potential synapses. These are segments with number of potential
// synapses permanence higher than some minimum threshold value.
// Potential synapses are synapses from presynaptc cells connected to the active cell.
// In other words, presynaptic cells define a statistical prediction that active cell will become the active in the next cycle.
// Bursting will create new segments if there are no matching segments until some matching segments appear.
// Once that happen, segment adoption will start.
// If some matching segments exist, bursting will grab the segment with most potential synapses and adapt it.
if (matchingSegments != null && matchingSegments.Count > 0)
{
DistalDendrite maxPotentialSeg = getSegmentwithHighesPotential(conn, matchingSegments);
for (int i = 0; i < matchingSegments.Count; i++)
{
matchingSegments[i].getIndex();
}
leastUsedCell = maxPotentialSeg.GetParentCell();
if (learn)
{
adaptSegment(conn, maxPotentialSeg, prevActiveCells, permanenceIncrement, permanenceDecrement);
int nGrowDesired = conn.getMaxNewSynapseCount() - conn.getLastActivity().PotentialSynapses[maxPotentialSeg.getIndex()];
if (nGrowDesired > 0)
{
growSynapses(conn, prevWinnerCells, maxPotentialSeg, conn.getInitialPermanence(),
nGrowDesired, random);
}
}
}
else
{
leastUsedCell = this.GetLeastUsedCell(conn, cells, random);
if (learn)
{
int nGrowExact = Math.Min(conn.getMaxNewSynapseCount(), prevWinnerCells.Count);
if (nGrowExact > 0)
{
DistalDendrite bestSegment = conn.CreateDistalSegment(leastUsedCell);
growSynapses(conn, prevWinnerCells, bestSegment, conn.getInitialPermanence(),
nGrowExact, random);
}
}
}
return(new BurstingResult(cells, leastUsedCell));
}
public void SerializeArrayCell()
{
HtmSerializer2 htm = new HtmSerializer2();
Cell[] cells = new Cell[2];
Cell[] cells1;
cells[0] = new Cell(12, 14, 16, 18, new CellActivity());
var distSeg1 = new DistalDendrite(cells[0], 1, 2, 2, 1.0, 100);
cells[0].DistalDendrites.Add(distSeg1);
var distSeg2 = new DistalDendrite(cells[0], 44, 24, 34, 1.0, 100);
cells[0].DistalDendrites.Add(distSeg2);
Cell preSynapticcell = new Cell(11, 14, 16, 18, new CellActivity());
var synapse1 = new Synapse(cells[0], distSeg1.SegmentIndex, 23, 1.0);
preSynapticcell.ReceptorSynapses.Add(synapse1);
var synapse2 = new Synapse(cells[0], distSeg2.SegmentIndex, 27, 1.0);
preSynapticcell.ReceptorSynapses.Add(synapse2);
cells[1] = new Cell(2, 4, 1, 8, new CellActivity());
var distSeg3 = new DistalDendrite(cells[1], 3, 4, 7, 1.0, 100);
cells[1].DistalDendrites.Add(distSeg3);
var distSeg4 = new DistalDendrite(cells[1], 4, 34, 94, 1.0, 100);
cells[1].DistalDendrites.Add(distSeg4);
Cell preSynapticcell1 = new Cell(1, 1, 6, 8, new CellActivity());
var synapse3 = new Synapse(cells[1], distSeg3.SegmentIndex, 23, 1.0);
preSynapticcell.ReceptorSynapses.Add(synapse1);
var synapse4 = new Synapse(cells[1], distSeg4.SegmentIndex, 27, 1.0);
preSynapticcell.ReceptorSynapses.Add(synapse2);
using (StreamWriter sw = new StreamWriter($"ser_{nameof(SerializeArrayCell)}.txt"))
{
htm.SerializeValue(cells, sw);
}
using (StreamReader sr = new StreamReader($"ser_{nameof(SerializeArrayCell)}.txt"))
{
//cells1 = htm.DeserializeCellArray(data,sr);
}
//Assert.IsTrue(cells.SequenceEqual(cells1));
}
public void CompareDentriteList()
{
Cell c1 = new Cell(1, 1, 10, 1, NeoCortexEntities.NeuroVisualizer.CellActivity.ActiveCell);
Cell c2 = new Cell(1, 1, 10, 1, NeoCortexEntities.NeuroVisualizer.CellActivity.ActiveCell);
Cell c3 = new Cell(2, 1, 10, 1, NeoCortexEntities.NeuroVisualizer.CellActivity.ActiveCell);
DistalDendrite d1 = new DistalDendrite(c1, 1, 1, 1, 0.5, 10);
DistalDendrite d2 = new DistalDendrite(c1, 1, 1, 1, 0.5, 10);
DistalDendrite d3 = new DistalDendrite(c1, 2, 1, 1, 0.5, 10);
DistalDendrite d4 = new DistalDendrite(c2, 2, 2, 1, 0.5, 10);
List <DistalDendrite> list1 = new List <DistalDendrite>()
{
d1, d2, d2
};
List <DistalDendrite> list2 = new List <DistalDendrite>()
{
d1, d2, d3
};
// Not same by reference
Assert.IsFalse(d1 == d2);
// d1 and d2 are same by value.
Assert.IsTrue(d1.Equals(d2));
// d1 and d3 are NOT same by value.
Assert.IsFalse(d1.Equals(d3));
// d3 and d4 are NOT same by value.
Assert.IsFalse(d3.Equals(d4));
// Lists are same by value.
list1.SequenceEqual(list2);
// All same by references.
list2 = new List <DistalDendrite>()
{
d1, d1, d1
};
// Lists are strill same by value.
list1.SequenceEqual(list2);
list2 = new List <DistalDendrite>()
{
d1, d2, d3
};
Assert.IsTrue(d1.Equals(d2));
Assert.IsFalse(d1.Equals(d3));
}
public void TestRecycleWeakestSynapseToMakeRoomForNewSynapse()
{
throw new AssertInconclusiveException("Not fixed.");
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = getDefaultParameters(null, KEY.CELLS_PER_COLUMN, 30);
p.Set(KEY.COLUMN_DIMENSIONS, new int[] { 100 });
//p.Set(KEY.COLUMN_DIMENSIONS, new int[] { 5 });
p = getDefaultParameters(p, KEY.MIN_THRESHOLD, 1);
p = getDefaultParameters(p, KEY.PERMANENCE_INCREMENT, 0.02);
p = getDefaultParameters(p, KEY.PERMANENCE_DECREMENT, 0.02);
p.Set(KEY.MAX_SYNAPSES_PER_SEGMENT, 3);
p.apply(cn);
tm.Init(cn);
Assert.AreEqual(3, cn.HtmConfig.MaxSynapsesPerSegment);
int[] prevActiveColumns = { 0, 1, 2 };
IList <Cell> prevWinnerCells = cn.GetCellSet(new int[] { 0, 1, 2 });
int[] activeColumns = { 4 };
DistalDendrite matchingSegment = cn.CreateDistalSegment(cn.GetCell(4));
cn.CreateSynapse(matchingSegment, cn.GetCell(81), 0.6);
// Weakest Synapse
cn.CreateSynapse(matchingSegment, cn.GetCell(0), 0.11);
ComputeCycle cc = tm.Compute(prevActiveColumns, true) as ComputeCycle;
Assert.IsTrue(prevWinnerCells.SequenceEqual(cc.WinnerCells));
tm.Compute(activeColumns, true);
//DD List<Synapse> synapses = cn.GetSynapses(matchingSegment);
List <Synapse> synapses = matchingSegment.Synapses;
Assert.AreEqual(3, synapses.Count);
//Set<Cell> presynapticCells = synapses.stream().map(s->s.getPresynapticCell()).collect(Collectors.toSet());
List <Cell> presynapticCells = new List <Cell>();
//DD foreach (var syn in cn.GetSynapses(matchingSegment))
foreach (var syn in matchingSegment.Synapses)
{
presynapticCells.Add(syn.GetPresynapticCell());
}
Assert.IsFalse(presynapticCells.Count(c => c.Index == 0) > 0);
//Assert.IsFalse(presynapticCells.stream().mapToInt(cell->cell.getIndex()).anyMatch(i->i == 0));
}
public void testRecycleLeastRecentlyActiveSegmentToMakeRoomForNewSegment()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = GetDefaultParameters(null, Parameters.KEY.CELLS_PER_COLUMN, 1);
p = GetDefaultParameters(p, Parameters.KEY.INITIAL_PERMANENCE, 0.5);
p = GetDefaultParameters(p, Parameters.KEY.PERMANENCE_INCREMENT, 0.02);
p = GetDefaultParameters(p, Parameters.KEY.PERMANENCE_DECREMENT, 0.02);
p.SetParameterByKey(Parameters.KEY.MAX_SEGMENTS_PER_CELL, 2);
p.Apply(cn);
TemporalMemory.Init(cn);
int[] prevActiveColumns1 = { 0, 1, 2 };
int[] prevActiveColumns2 = { 3, 4, 5 };
int[] prevActiveColumns3 = { 6, 7, 8 };
int[] activeColumns = { 9 };
Cell cell9 = cn.GetCell(9);
tm.Compute(cn, prevActiveColumns1, true);
tm.Compute(cn, activeColumns, true);
Assert.AreEqual(1, cn.GetSegments(cell9).Count);
DistalDendrite oldestSegment = cn.GetSegments(cell9)[0];
tm.Reset(cn);
tm.Compute(cn, prevActiveColumns2, true);
tm.Compute(cn, activeColumns, true);
Assert.AreEqual(2, cn.GetSegments(cell9).Count);
HashSet <Cell> oldPresynaptic = new HashSet <Cell>(cn.GetSynapses(oldestSegment)
.Select(s => s.GetPresynapticCell()));
tm.Reset(cn);
tm.Compute(cn, prevActiveColumns3, true);
tm.Compute(cn, activeColumns, true);
Assert.AreEqual(2, cn.GetSegments(cell9).Count);
// Verify none of the segments are connected to the cells the old
// segment was connected to.
foreach (DistalDendrite segment in cn.GetSegments(cell9))
{
HashSet <Cell> newPresynaptic = new HashSet <Cell>(cn.GetSynapses(segment)
.Select(s => s.GetPresynapticCell()));
//.collect(Collectors.toSet());
Assert.IsFalse(oldPresynaptic.Overlaps(newPresynaptic));
//Assert.IsTrue(Collections.disjoint(oldPresynaptic, newPresynaptic));
}
}
/**
* Updates synapses on segment.
* Strengthens active synapses; weakens inactive synapses.
*
* @param conn {@link Connections} instance for the tm
* @param segment {@link DistalDendrite} to adapt
* @param prevActiveCells Active {@link Cell}s in `t-1`
* @param permanenceIncrement Amount to increment active synapses
* @param permanenceDecrement Amount to decrement inactive synapses
*/
public void adaptSegment(Connections conn, DistalDendrite segment, ICollection <Cell> prevActiveCells,
double permanenceIncrement, double permanenceDecrement)
{
// Destroying a synapse modifies the set that we're iterating through.
List <Synapse> synapsesToDestroy = new List <Synapse>();
foreach (Synapse synapse in conn.getSynapses(segment))
{
double permanence = synapse.getPermanence();
//
// If synapse's presynaptic cell was active in the previous cycle then streng it.
if (prevActiveCells.Contains(synapse.getPresynapticCell()))
{
permanence += permanenceIncrement;
}
else
{
permanence -= permanenceDecrement;
}
// Keep permanence within min/max bounds
permanence = permanence <0 ? 0 : permanence> 1.0 ? 1.0 : permanence;
// Use this to examine issues caused by subtle floating point differences
// be careful to set the scale (1 below) to the max significant digits right of the decimal point
// between the permanenceIncrement and initialPermanence
//
// permanence = new BigDecimal(permanence).setScale(1, RoundingMode.HALF_UP).doubleValue();
if (permanence < EPSILON)
{
synapsesToDestroy.Add(synapse);
}
else
{
synapse.setPermanence(conn.getSynPermConnected(), permanence);
}
}
foreach (Synapse s in synapsesToDestroy)
{
conn.destroySynapse(s, segment);
}
if (conn.GetNumSynapses(segment) == 0)
{
conn.destroySegment(segment);
}
}
public void CompareDentrites()
{
Cell c1 = new Cell(1, 1, 10, 1, NeoCortexEntities.NeuroVisualizer.CellActivity.ActiveCell);
Cell c2 = new Cell(1, 1, 10, 1, NeoCortexEntities.NeuroVisualizer.CellActivity.ActiveCell);
Cell c3 = new Cell(2, 1, 10, 1, NeoCortexEntities.NeuroVisualizer.CellActivity.ActiveCell);
DistalDendrite d1 = new DistalDendrite(c1, 1, 1, 1, 0.5, 10);
DistalDendrite d2 = new DistalDendrite(c1, 1, 1, 1, 0.5, 10);
DistalDendrite d3 = new DistalDendrite(c1, 2, 1, 1, 0.5, 10);
Assert.IsTrue(d1.Equals(d2));
Assert.IsFalse(d1.Equals(d3));
}
/// <summary>
/// Gets the segment with maximal potential. Segment's potential is measured by number of potential synapses.
/// </summary>
/// <param name="conn"></param>
/// <param name="matchingSegments"></param>
/// <returns></returns>
private DistalDendrite getSegmentwithHighesPotential(Connections conn, List <DistalDendrite> matchingSegments)
{
// int[] numActPotential = conn.getLastActivity().numActivePotential;
DistalDendrite maxSeg = matchingSegments[0];
for (int i = 0; i < matchingSegments.Count - 1; i++)
{
if (conn.getLastActivity().PotentialSynapses[matchingSegments[i + 1].getIndex()] > conn.getLastActivity().PotentialSynapses[matchingSegments[i].getIndex()])
{
maxSeg = matchingSegments[i + 1];
}
}
return(maxSeg);
}
/**
* Activates all of the cells in an unpredicted active column,
* chooses a winner cell, and, if learning is turned on, either adapts or
* creates a segment. growSynapses is invoked on this segment.
* </p><p>
* <b>Pseudocode:</b>
* </p><p>
* <pre>
* mark all cells as active
* if there are any matching distal dendrite segments
* find the most active matching segment
* mark its cell as a winner cell
* (learning)
* grow and reinforce synapses to previous winner cells
* else
* find the cell with the least segments, mark it as a winner cell
* (learning)
* (optimization) if there are previous winner cells
* add a segment to this winner cell
* grow synapses to previous winner cells
* </pre>
* </p>
*
* @param conn Connections instance for the TM
* @param column Bursting {@link Column}
* @param matchingSegments List of matching {@link DistalDendrite}s
* @param prevActiveCells Active cells in `t-1`
* @param prevWinnerCells Winner cells in `t-1`
* @param permanenceIncrement Amount by which permanences of synapses
* are decremented during learning
* @param permanenceDecrement Amount by which permanences of synapses
* are incremented during learning
* @param random Random number generator
* @param learn Whether or not learning is enabled
*
* @return Tuple containing:
* cells list of the processed column's cells
* bestCell the best cell
*/
public Tuple BurstColumn(Connections conn, Column column, List <DistalDendrite> matchingSegments,
HashSet <Cell> prevActiveCells, HashSet <Cell> prevWinnerCells, double permanenceIncrement, double permanenceDecrement,
IRandom random, bool learn)
{
IList <Cell> cells = column.GetCells();
Cell bestCell = null;
if (matchingSegments.Any())
{
int[] numPoten = conn.GetLastActivity().numActivePotential;
Comparison <DistalDendrite> cmp = (dd1, dd2) => numPoten[dd1.GetIndex()] - numPoten[dd2.GetIndex()];
var sortedSegments = new List <DistalDendrite>(matchingSegments);
sortedSegments.Sort(cmp);
DistalDendrite bestSegment = sortedSegments.Last();
bestCell = bestSegment.GetParentCell();
if (learn)
{
AdaptSegment(conn, bestSegment, prevActiveCells, permanenceIncrement, permanenceDecrement);
int nGrowDesired = conn.GetMaxNewSynapseCount() - numPoten[bestSegment.GetIndex()];
if (nGrowDesired > 0)
{
GrowSynapses(conn, prevWinnerCells, bestSegment, conn.GetInitialPermanence(),
nGrowDesired, random);
}
}
}
else
{
bestCell = LeastUsedCell(conn, cells, random);
if (learn)
{
int nGrowExact = Math.Min(conn.GetMaxNewSynapseCount(), prevWinnerCells.Count);
if (nGrowExact > 0)
{
DistalDendrite bestSegment = conn.CreateSegment(bestCell);
GrowSynapses(conn, prevWinnerCells, bestSegment, conn.GetInitialPermanence(),
nGrowExact, random);
}
}
}
return(new Tuple(cells, bestCell));
}
public void testAdaptSegmentToMin()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = Parameters.GetAllDefaultParameters();
p.Apply(cn);
TemporalMemory.Init(cn);
DistalDendrite dd = cn.CreateSegment(cn.GetCell(0));
Synapse s1 = cn.CreateSynapse(dd, cn.GetCell(23), 0.1);
cn.CreateSynapse(dd, cn.GetCell(1), 0.3);
tm.AdaptSegment(cn, dd, cn.GetCellSet(), cn.GetPermanenceIncrement(), cn.GetPermanenceDecrement());
Assert.IsFalse(cn.GetSynapses(dd).Contains(s1));
}
public void SerializePoolTest(int size, int numInputs)
{
Pool pool = new Pool(size, numInputs);
//pool.m_SynapseConnections = new List<int>();
//pool.m_SynapseConnections.Add(34);
//pool.m_SynapseConnections.Add(87);
//pool.m_SynapseConnections.Add(44);
Cell cell = new Cell(12, 14, 16, 18, new CellActivity());
var distSeg1 = new DistalDendrite(cell, 1, 2, 2, 1.0, 100);
cell.DistalDendrites.Add(distSeg1);
var distSeg2 = new DistalDendrite(cell, 44, 24, 34, 1.0, 100);
cell.DistalDendrites.Add(distSeg2);
Cell preSynapticcell = new Cell(11, 14, 16, 28, new CellActivity());
var synapse1 = new Synapse(cell, distSeg1.SegmentIndex, 23, 1.0);
preSynapticcell.ReceptorSynapses.Add(synapse1);
var synapse2 = new Synapse(cell, distSeg2.SegmentIndex, 27, 1.0);
preSynapticcell.ReceptorSynapses.Add(synapse2);
pool.m_SynapsesBySourceIndex = new Dictionary <int, Synapse>();
pool.m_SynapsesBySourceIndex.Add(3, synapse1);
pool.m_SynapsesBySourceIndex.Add(67, synapse2);
using (StreamWriter sw = new StreamWriter($"ser_{nameof(SerializePoolTest)}.txt"))
{
pool.Serialize(sw);
}
using (StreamReader sr = new StreamReader($"ser_{nameof(SerializePoolTest)}.txt"))
{
Pool pool1 = Pool.Deserialize(sr);
Assert.IsTrue(pool1.Equals(pool));
}
}
public void TestActiveSegmentGrowSynapsesAccordingToPotentialOverlap()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = getDefaultParameters(null, KEY.CELLS_PER_COLUMN, 1);
p = getDefaultParameters(p, KEY.MIN_THRESHOLD, 1);
p = getDefaultParameters(p, KEY.ACTIVATION_THRESHOLD, 2);
p = getDefaultParameters(p, KEY.MAX_NEW_SYNAPSE_COUNT, 4);
p.apply(cn);
tm.Init(cn);
// Use 1 cell per column so that we have easy control over the winner cells.
int[] previousActiveColumns = { 0, 1, 2, 3, 4 };
List <Cell> prevWinnerCells = new List <Cell>(new Cell[] { cn.GetCell(0), cn.GetCell(1), cn.GetCell(2), cn.GetCell(3), cn.GetCell(4) });
int[] activeColumns = { 5 };
DistalDendrite activeSegment = cn.CreateDistalSegment(cn.GetCell(5));
cn.CreateSynapse(activeSegment, cn.GetCell(0), 0.5);
cn.CreateSynapse(activeSegment, cn.GetCell(1), 0.5);
cn.CreateSynapse(activeSegment, cn.GetCell(2), 0.2);
ComputeCycle cc = tm.Compute(previousActiveColumns, true) as ComputeCycle;
Assert.IsTrue(prevWinnerCells.SequenceEqual(cc.WinnerCells));
cc = tm.Compute(activeColumns, true) as ComputeCycle;
List <Cell> presynapticCells = new List <Cell>();
foreach (var syn in activeSegment.GetAllSynapses(cn))
{
presynapticCells.Add(syn.getPresynapticCell());
}
//= cn.getSynapses(activeSegment).stream()
//.map(s->s.getPresynapticCell())
//.collect(Collectors.toSet());
Assert.IsTrue(
presynapticCells.Count == 4 && (
(presynapticCells.Contains(cn.GetCell(0)) && presynapticCells.Contains(cn.GetCell(1)) && presynapticCells.Contains(cn.GetCell(2)) && presynapticCells.Contains(cn.GetCell(3))) ||
(presynapticCells.Contains(cn.GetCell(0)) && presynapticCells.Contains(cn.GetCell(1)) && presynapticCells.Contains(cn.GetCell(2)) && presynapticCells.Contains(cn.GetCell(4)))));
}
public void SerializeSegmentTest()
{
//TODO
Cell cell = new Cell(12, 14, 16, 18, new CellActivity());
Segment seg = new DistalDendrite(cell, 1, 2, 2, 1.0, 100);
using (StreamWriter sw = new StreamWriter($"ser_{nameof(SerializeSegmentTest)}.txt"))
{
seg.Serialize(sw);
}
using (StreamReader sr = new StreamReader($"ser_{nameof(SerializeSegmentTest)}.txt"))
{
//Segment segment1 = Segment.Deserialize(sr);
// Assert.IsTrue(segment1.Equals(seg));
}
}
public void SerializeDistalDendrite()
{
Cell cell = new Cell(1, 1, 1, 1, new CellActivity());
DistalDendrite distal = new DistalDendrite(cell, 1, 2, 2, 1.0, 100);
//distal.Synapses.Add(new Synapse(cell, 1, 23, 1.0));
//distal.Synapses.Add(new Synapse(cell, 3, 27, 1.0));
using (StreamWriter sw = new StreamWriter($"ser_{nameof(SerializeDistalDendrite)}.txt"))
{
distal.Serialize(sw);
}
using (StreamReader sr = new StreamReader($"ser_{nameof(SerializeDistalDendrite)}.txt"))
{
DistalDendrite distal1 = DistalDendrite.Deserialize(sr);
Assert.IsTrue(distal1.Equals(distal));
}
}
public void TestAdaptSegmentToMin()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = Parameters.getAllDefaultParameters();
p.apply(cn);
tm.Init(cn);
DistalDendrite dd = cn.CreateDistalSegment(cn.GetCell(0));
Synapse s1 = cn.CreateSynapse(dd, cn.GetCell(23), 0.1);
cn.CreateSynapse(dd, cn.GetCell(1), 0.3);
TemporalMemory.AdaptSegment(cn, dd, cn.GetCellSet(new int[] { }), cn.HtmConfig.PermanenceIncrement, cn.HtmConfig.PermanenceDecrement);
//DD Assert.IsFalse(cn.GetSynapses(dd).Contains(s1));
Assert.IsFalse(dd.Synapses.Contains(s1));
}
public void testActiveSegmentGrowSynapsesAccordingToPotentialOverlap()
{
TemporalMemory tm = new TemporalMemory();
Connections cn = new Connections();
Parameters p = GetDefaultParameters(null, Parameters.KEY.CELLS_PER_COLUMN, 1);
p = GetDefaultParameters(p, Parameters.KEY.MIN_THRESHOLD, 1);
p = GetDefaultParameters(p, Parameters.KEY.ACTIVATION_THRESHOLD, 2);
p = GetDefaultParameters(p, Parameters.KEY.MAX_NEW_SYNAPSE_COUNT, 4);
p.Apply(cn);
TemporalMemory.Init(cn);
// Use 1 cell per column so that we have easy control over the winner cells.
int[] previousActiveColumns = { 0, 1, 2, 3, 4 };
HashSet <Cell> prevWinnerCells = new HashSet <Cell>(Arrays.AsList(0, 1, 2, 3, 4)
.Select(i => cn.GetCell(i))
.ToList());
int[] activeColumns = { 5 };
DistalDendrite activeSegment = cn.CreateSegment(cn.GetCell(5));
cn.CreateSynapse(activeSegment, cn.GetCell(0), 0.5);
cn.CreateSynapse(activeSegment, cn.GetCell(1), 0.5);
cn.CreateSynapse(activeSegment, cn.GetCell(2), 0.2);
ComputeCycle cc = tm.Compute(cn, previousActiveColumns, true);
Assert.IsTrue(prevWinnerCells.SetEquals(cc.WinnerCells()));
cc = tm.Compute(cn, activeColumns, true);
HashSet <Cell> presynapticCells = new HashSet <Cell>(cn.GetSynapses(activeSegment)
.Select(s => s.GetPresynapticCell())
.ToList());
Assert.IsTrue(
presynapticCells.Count == 4 && (
!presynapticCells.Except(new List <Cell> {
cn.GetCell(0), cn.GetCell(1), cn.GetCell(2), cn.GetCell(3)
}).Any() ||
!presynapticCells.Except(new List <Cell> {
cn.GetCell(0), cn.GetCell(1), cn.GetCell(2), cn.GetCell(4)
}).Any()));
}
