class ExtendedTMCPP_ApicalTiebreakTests(ApicalTiebreakTestBase,
unittest.TestCase):
"""
Run the apical tiebreak tests on the C++ ExtendedTemporalMemory.
"""
def constructTM(self, columnCount, basalInputSize, apicalInputSize,
cellsPerColumn, initialPermanence, connectedPermanence,
minThreshold, sampleSize, permanenceIncrement,
permanenceDecrement, predictedSegmentDecrement,
activationThreshold, seed):
params = {
"columnDimensions": (columnCount,),
"basalInputDimensions": (basalInputSize,),
"apicalInputDimensions": (apicalInputSize,),
"cellsPerColumn": cellsPerColumn,
"initialPermanence": initialPermanence,
"connectedPermanence": connectedPermanence,
"minThreshold": minThreshold,
"maxNewSynapseCount": sampleSize,
"permanenceIncrement": permanenceIncrement,
"permanenceDecrement": permanenceDecrement,
"predictedSegmentDecrement": predictedSegmentDecrement,
"activationThreshold": activationThreshold,
"seed": seed,
"learnOnOneCell": False,
"formInternalBasalConnections": False,
}
self.tm = ExtendedTemporalMemory(**params)
def compute(self, activeColumns, basalInput, apicalInput, learn):
activeColumns = sorted(activeColumns)
basalInput = sorted(basalInput)
apicalInput = sorted(apicalInput)
# Use depolarizeCells + activateCells rather than tm.compute so that
# getPredictiveCells returns predictions for the current timestep.
self.tm.depolarizeCells(activeCellsExternalBasal=basalInput,
activeCellsExternalApical=apicalInput,
learn=learn)
self.tm.activateCells(activeColumns,
reinforceCandidatesExternalBasal=basalInput,
growthCandidatesExternalBasal=basalInput,
reinforceCandidatesExternalApical=apicalInput,
growthCandidatesExternalApical=apicalInput,
learn=learn)
def getActiveCells(self):
return self.tm.getActiveCells()
def getPredictedCells(self):
return self.tm.getPredictiveCells()
class ExtendedTMCPP_SequenceMemoryTests(SequenceMemoryTestBase,
unittest.TestCase):
"""
Run the sequence memory tests on the C++ ExtendedTemporalMemory.
"""
def constructTM(self, columnCount, cellsPerColumn, initialPermanence,
connectedPermanence, minThreshold, sampleSize,
permanenceIncrement, permanenceDecrement,
predictedSegmentDecrement, activationThreshold, seed):
params = {
"columnDimensions": (columnCount,),
"cellsPerColumn": cellsPerColumn,
"initialPermanence": initialPermanence,
"connectedPermanence": connectedPermanence,
"minThreshold": minThreshold,
"maxNewSynapseCount": sampleSize,
"permanenceIncrement": permanenceIncrement,
"permanenceDecrement": permanenceDecrement,
"predictedSegmentDecrement": predictedSegmentDecrement,
"activationThreshold": activationThreshold,
"seed": seed,
"learnOnOneCell": False,
}
self.tm = ExtendedTemporalMemory(**params)
def compute(self, activeColumns, learn):
# Use depolarizeCells + activateCells rather than tm.compute so that
# getPredictiveCells returns predictions for the current timestep.
self.tm.depolarizeCells(learn=learn)
self.tm.activateCells(sorted(activeColumns), learn=learn)
def reset(self):
self.tm.reset()
def getActiveCells(self):
return self.tm.getActiveCells()
def getPredictedCells(self):
return self.tm.getPredictiveCells()