// Return a segmentUpdate data structure containing a list of proposed changes to segment.
// Let activeSynapses be the list of active synapses where the originating cells have
// their activeState output = 1 at time step t.
// (This list is empty if s = -1 since the segment doesn't exist.) newSynapses is an optional argument
// that defaults to false. If newSynapses is true, then newSynapseCount - count(activeSynapses) synapses
// are added to activeSynapses. These synapses are randomly chosen from the set of cells that have
// learnState output = 1 at time step t.
public SegmentUpdate GetSegmentActiveSynapses(int t, HTMSegment segment = null, bool newSynapses = false)
{
SegmentUpdate segmentUpdate = new SegmentUpdate();
segmentUpdate.ActiveSynapses = new List <HTMSynapse>();
segmentUpdate.NewSynapses = new List <HTMCell>();
segmentUpdate.AddNewSynapses = newSynapses;
segmentUpdate.Segment = segment;
if (segmentUpdate.Segment != null)
{
segmentUpdate.ActiveSynapses = segment.GetActiveSynapses(t, false, false);
}
if (!newSynapses)
{
return(segmentUpdate);
}
int newSynapseCount = Math.Max(0, _newSynapseCount - segmentUpdate.ActiveSynapses.Count);
//List<HTMCell> learningCells = GetRandomActiveCells(t);
List <HTMCell> learningCells = GetRandomLearningCells(t);
newSynapseCount = Math.Min(newSynapseCount, learningCells.Count);
// Truncate the array of learning cells. To do : get a random sample of the array.
for (int i = 0; i < newSynapseCount; i++)
{
segmentUpdate.NewSynapses.Add(learningCells[i]);
}
return(segmentUpdate);
}
// Return a segment that is/was active at time t.
// If multiple segments are active, sequence segments are given preference.
// Otherwise, segments with most activity are given preference.
public HTMSegment GetActiveSegment(int t)
{
List <HTMSegment> activeSegs = new List <HTMSegment>();
foreach (HTMSegment seg in _distalSegments)
{
if (seg.GetActive(-1, false, false))
{
activeSegs.Add(seg);
}
}
if (activeSegs.Count == 0)
{
return(null);
}
else if (activeSegs.Count == 1)
{
return(activeSegs[0]);
}
// There're more the one active segments so sequence segments given priority.
List <HTMSegment> sequenceSegs = new List <HTMSegment>();
foreach (HTMSegment seg in activeSegs)
{
if (seg.IsSequence)
{
sequenceSegs.Add(seg);
}
}
if (sequenceSegs.Count == 1)
{
return(sequenceSegs[0]);
}
else if (sequenceSegs.Count > 1)
{
activeSegs = sequenceSegs;
}
// Search the segment that had, in the previous step, the highest activity measured by the number of active synapses.
HTMSegment mostActiveSegment = null;
int maxActivity = int.MinValue;
int activity;
foreach (HTMSegment seg in activeSegs)
{
activity = seg.GetActivity(-1);
if (activity > maxActivity)
{
maxActivity = activity;
mostActiveSegment = seg;
}
}
return(mostActiveSegment);
}
// For the given column, return the cell with the best matching segment.
// If no cell has a matching segment, then return the cell with the fewest number of segments.
public CellSegmentInfo GetBestMatchingCell(bool sequence, int t)
{
HTMCell bestCell = null;
HTMSegment bestSeg = null;
int bestCount = 0;
HTMSegment seg;
int synapseCount;
foreach (HTMCell cell in _cells)
{
seg = cell.GetBestMatchingSegment(t, sequence);
// TO DO . to study in depth. the previsous function is aggressive in finding the segment but
// nevertheless exclude segment with activation under minThreshold, this could bring
// to add step by step similar segments?
if (seg != null)
{
synapseCount = seg.GetActiveSynapses(t, false, false).Count;
if (synapseCount > bestCount)
{
bestCell = cell;
bestSeg = seg;
bestCount = synapseCount;
}
}
}
if (bestCell == null)
{
int fewestSegmentCount = int.MaxValue;
foreach (HTMCell cell in _cells)
{
if (cell.DistalSegments.Count < fewestSegmentCount)
{
fewestSegmentCount = cell.DistalSegments.Count;
bestCell = cell;
//if (cell.DistalSegments.Count > 0)
// bestSeg = cell.DistalSegments[0]; // choose the first segment
}
}
}
CellSegmentInfo cellSegmentInfo = new CellSegmentInfo();
cellSegmentInfo.Cell = bestCell;
cellSegmentInfo.Segment = bestSeg;
return(cellSegmentInfo);
}
// Find the segment with the largest number of active synapses.
// This routine is aggressive in finding the best match.
// The permanence value of synapses is allowed to be below connectedPerm.
// The number of active synapses is allowed to be below activationThreshold,
// but must be above minThreshold.
public HTMSegment GetBestMatchingSegment(int t, bool sequence)
{
HTMSegment bestSegment = null;
int bestSynapseCount = _column.Region.MinSegmentActivityForLearning;
int synCount;
foreach (HTMSegment seg in _distalSegments)
{
synCount = seg.GetActiveSynapses(t, false, false).Count;
if (synCount > bestSynapseCount)
{
bestSynapseCount = synCount;
bestSegment = seg;
}
}
return(bestSegment);
}
double _y; // The x-position of the column inside the matrix. Range from 0 to 1.
#endregion Fields
#region Constructors
public HTMColumn(HTMRegionAgent region, int posX, int posY, double x, double y)
{
_region = region;
_posX = posX;
_posY = posY;
_x = x;
_y = y;
_cells = new List<HTMCell>();
for (int i = 0; i < region.CellsPerColumn; i++)
_cells.Add(new HTMCell(this, i));
_proximalSegment = new HTMSegment(null, _region.SegmentActivationThreshold);
_isActive = false;
_overlap = 0;
_boost = 1.0;
_activeDutyCycle = 1.0;
_overlapDutyCycle = 1.0;
}
public HTMColumn(HTMRegionAgent region, int posX, int posY, double x, double y)
{
_region = region;
_posX = posX;
_posY = posY;
_x = x;
_y = y;
_cells = new List <HTMCell>();
for (int i = 0; i < region.CellsPerColumn; i++)
{
_cells.Add(new HTMCell(this, i));
}
_proximalSegment = new HTMSegment(null, _region.SegmentActivationThreshold);
_isActive = false;
_overlap = 0;
_boost = 1.0;
_activeDutyCycle = 1.0;
_overlapDutyCycle = 1.0;
}
public void StepTemporalPooling()
{
// Phase 1
// From the Numenta Docs:
// The first phase calculates the active state for each cell.
// For each winning column we determine which cells should become active.
// If the bottom-up input was predicted by any cell (i.e. its predictiveState was 1 due to
// a sequence segment in the previous time step), then those cells become active (lines 4-9).
// If the bottom-up input was unexpected (i.e. no cells had predictiveState output on),
// then each cell in the column becomes active (lines 11-13).
foreach (HTMColumn col in _activeColumns)
{
bool buPredicted = false;
bool lcChosen = false;
foreach (HTMCell cell in col.Cells)
{
if (cell.GetPredicting(-1))
{
//
_correctPrediction++;
HTMSegment segment = cell.GetActiveSegment(-1);
if (segment != null && segment.IsSequence)
{
buPredicted = true;
cell.SetActive(true);
if (_doTemporalLearning)
{
if (segment.GetActive(-1, true, false))
{
lcChosen = true;
cell.SetLearning(true);
}
}
}
}
}
if (!buPredicted)
{
foreach (HTMCell cell in col.Cells)
{
cell.SetActive(true);
}
}
// If the bottom-up input was not predicted, the best matching cell is chosen as the learning cell and a new segment is added to that cell.
if (_doTemporalLearning)
{
if (!lcChosen)
{
CellSegmentInfo bestCellSegmentInfo = col.GetBestMatchingCell(true, -1);
bestCellSegmentInfo.Cell.SetLearning(true);
SegmentUpdate segmentToUpdate = bestCellSegmentInfo.Cell.GetSegmentActiveSynapses(-1, bestCellSegmentInfo.Segment, true);
segmentToUpdate.IsSequence = true;
if (segmentToUpdate.Segment != null || (segmentToUpdate.AddNewSynapses && segmentToUpdate.NewSynapses.Count > 0)) // queue the update only if necessary
{
bestCellSegmentInfo.Cell.SegmentUpdateList.Add(segmentToUpdate);
}
}
}
}
// Phase 2
// The second phase calculates the predictive state for each cell.
// A cell will turn on its predictive state output if one of its segments becomes active,
// i.e. if enough of its lateral inputs are currently active due to feed-forward input.
// In this case, the cell queues up the following changes:
// a) reinforcement of the currently active segment (lines 47-48),
// and b) reinforcement of a segment that could have predicted this activation,
// i.e. a segment that has a (potentially weak) match to activity during the previous time step (lines 50-53).
foreach (HTMColumn col in _columns)
{
foreach (HTMCell cell in col.Cells)
{
//if (cell.GetActive(0)) // Cells with active dendrite segments are put in the predictive state UNLESS they are already active due to feed-forward input.
// continue;
foreach (HTMSegment seg in cell.DistalSegments)
{
if (!seg.GetActive(0, false, false))
{
continue;
}
cell.SetPredicting(true);
// TO DO : check. Active and predictive state are mutual exclusive?
// if so, the changing from active to predicting must be done
// through a temporary array to avoid cell asymmetrical behavior.
//cell.SetActive(false);
if (_doTemporalLearning)
{
// a) reinforcement of the currently active segment
SegmentUpdate activeSegUpdate = cell.GetSegmentActiveSynapses(0, seg);
cell.SegmentUpdateList.Add(activeSegUpdate);
// b) reinforcement of a segment that could have predicted this activation,
HTMSegment predSegment = cell.GetBestMatchingSegment(-1, true);
if (predSegment == null)
{
continue;
}
SegmentUpdate predSegUpdate = cell.GetSegmentActiveSynapses(-1, predSegment, true);
cell.SegmentUpdateList.Add(predSegUpdate);
}
}
}
}
// Phase 3
// The third and last phase actually carries out learning.
// In this phase segment updates that have been queued up are actually
// implemented once we get feed-forward input and the cell is chosen
// as a learning cell (lines 56-57). Otherwise,
// if the cell ever stops predicting for any reason,
// we negatively reinforce the segments (lines 58-60).
if (_doTemporalLearning)
{
foreach (HTMColumn col in _columns)
{
foreach (HTMCell cell in col.Cells)
{
if (cell.SegmentUpdateList.Count == 0) // if there isn't segment to adapt then continue.
{
continue;
}
if (cell.GetLearning(0))
{
// once we get feed-forward input and the cell is chosen as a learning cell
cell.AdaptSegments(true);
}
else // if (!cell.GetPredicting(0) && cell.GetPredicting(-1))
{
// if the cell ever stops predicting for any reason,
// we negatively reinforce the segments
cell.AdaptSegments(false);
}
}
}
}
}
// Return a segmentUpdate data structure containing a list of proposed changes to segment.
// Let activeSynapses be the list of active synapses where the originating cells have
// their activeState output = 1 at time step t.
// (This list is empty if s = -1 since the segment doesn't exist.) newSynapses is an optional argument
// that defaults to false. If newSynapses is true, then newSynapseCount - count(activeSynapses) synapses
// are added to activeSynapses. These synapses are randomly chosen from the set of cells that have
// learnState output = 1 at time step t.
public SegmentUpdate GetSegmentActiveSynapses(int t, HTMSegment segment = null, bool newSynapses = false)
{
SegmentUpdate segmentUpdate = new SegmentUpdate();
segmentUpdate.ActiveSynapses = new List<HTMSynapse>();
segmentUpdate.NewSynapses = new List<HTMCell>();
segmentUpdate.AddNewSynapses = newSynapses;
segmentUpdate.Segment = segment;
if (segmentUpdate.Segment != null)
segmentUpdate.ActiveSynapses = segment.GetActiveSynapses(t, false, false);
if (!newSynapses)
return segmentUpdate;
int newSynapseCount = Math.Max(0, _newSynapseCount - segmentUpdate.ActiveSynapses.Count);
//List<HTMCell> learningCells = GetRandomActiveCells(t);
List<HTMCell> learningCells = GetRandomLearningCells(t);
newSynapseCount = Math.Min(newSynapseCount, learningCells.Count);
// Truncate the array of learning cells. To do : get a random sample of the array.
for (int i = 0 ; i < newSynapseCount; i++)
segmentUpdate.NewSynapses.Add(learningCells[i]);
return segmentUpdate;
}
// This function iterates through a list of segmentUpdate's and reinforces each segment.
// For each segmentUpdate element, the following changes are performed. If positiveReinforcement is true
// then synapses on the active list get their permanence counts incremented by permanenceInc.
// All other synapses get their permanence counts decremented by permanenceDec.
// If positiveReinforcement is false, then synapses on the active list get their permanence counts
// decremented by permanenceDec. After this step, any synapses in segmentUpdate that do yet exist
// get added with a permanence count of initialPerm.
public void AdaptSegments(bool positiveReinforcement)
{
foreach (SegmentUpdate segInfo in _segmentUpdateList)
{
if (segInfo.Segment != null)
{
if (positiveReinforcement)
{
foreach (HTMSynapse syn in segInfo.Segment.Synapses)
if (segInfo.ActiveSynapses.Contains(syn))
syn.IncreasePermanence();
else
syn.DecreasePermanence();
}
else
foreach (HTMSynapse syn in segInfo.ActiveSynapses)
syn.DecreasePermanence();
// TO DO : the series of negative reinforcements should bring to eliminate the entire segment.
}
if (segInfo.AddNewSynapses && segInfo.NewSynapses.Count > 0)
{
// check wheter exist a similar segment
bool isFound = false;
foreach (HTMSegment seg in _distalSegments)
{
int foundCount = 0;
foreach (HTMSynapse syn in seg.Synapses)
if (segInfo.NewSynapses.Contains(syn.InputCell))
foundCount++;
if (foundCount == segInfo.NewSynapses.Count)
{
isFound = true;
break;
}
}
if (isFound)
continue;
// update or create a segment
HTMSegment segment;
if (segInfo.Segment != null)
segment = segInfo.Segment;
else
{
segment = new HTMSegment(this, _column.Region.SegmentActivationThreshold);
_distalSegments.Add(segment);
_column.Region.Director.Log("Created new distal segment on a cell on column " + segment.Cell.Column.PosX.ToString() + "," + segment.Cell.Column.PosY.ToString());
}
segment.IsSequence = segInfo.IsSequence;
foreach (HTMCell cell in segInfo.NewSynapses)
{
//
bool find = false;
foreach (HTMSynapse syn in segment.Synapses)
{
if (syn.InputCell == cell)
{
find = true;
break;
}
}
//
if (!find)
segment.Synapses.Add(new HTMSynapse(cell));
}
}
}
_segmentUpdateList.Clear();
}
// This function iterates through a list of segmentUpdate's and reinforces each segment.
// For each segmentUpdate element, the following changes are performed. If positiveReinforcement is true
// then synapses on the active list get their permanence counts incremented by permanenceInc.
// All other synapses get their permanence counts decremented by permanenceDec.
// If positiveReinforcement is false, then synapses on the active list get their permanence counts
// decremented by permanenceDec. After this step, any synapses in segmentUpdate that do yet exist
// get added with a permanence count of initialPerm.
public void AdaptSegments(bool positiveReinforcement)
{
foreach (SegmentUpdate segInfo in _segmentUpdateList)
{
if (segInfo.Segment != null)
{
if (positiveReinforcement)
{
foreach (HTMSynapse syn in segInfo.Segment.Synapses)
{
if (segInfo.ActiveSynapses.Contains(syn))
{
syn.IncreasePermanence();
}
else
{
syn.DecreasePermanence();
}
}
}
else
{
foreach (HTMSynapse syn in segInfo.ActiveSynapses)
{
syn.DecreasePermanence();
}
}
// TO DO : the series of negative reinforcements should bring to eliminate the entire segment.
}
if (segInfo.AddNewSynapses && segInfo.NewSynapses.Count > 0)
{
// check wheter exist a similar segment
bool isFound = false;
foreach (HTMSegment seg in _distalSegments)
{
int foundCount = 0;
foreach (HTMSynapse syn in seg.Synapses)
{
if (segInfo.NewSynapses.Contains(syn.InputCell))
{
foundCount++;
}
}
if (foundCount == segInfo.NewSynapses.Count)
{
isFound = true;
break;
}
}
if (isFound)
{
continue;
}
// update or create a segment
HTMSegment segment;
if (segInfo.Segment != null)
{
segment = segInfo.Segment;
}
else
{
segment = new HTMSegment(this, _column.Region.SegmentActivationThreshold);
_distalSegments.Add(segment);
_column.Region.Director.Log("Created new distal segment on a cell on column " + segment.Cell.Column.PosX.ToString() + "," + segment.Cell.Column.PosY.ToString());
}
segment.IsSequence = segInfo.IsSequence;
foreach (HTMCell cell in segInfo.NewSynapses)
{
//
bool find = false;
foreach (HTMSynapse syn in segment.Synapses)
{
if (syn.InputCell == cell)
{
find = true;
break;
}
}
//
if (!find)
{
segment.Synapses.Add(new HTMSynapse(cell));
}
}
}
}
_segmentUpdateList.Clear();
}
