def __init__(self, columnCount, inputWidth, historyLength,
minHistory, poolerType, **kwargs):
if columnCount <= 0 or inputWidth <=0:
raise TypeError("Parameters columnCount and inputWidth must be > 0")
# Pull out the pooler arguments automatically
# These calls whittle down kwargs and create instance variables of TemporalPoolerRegion
self._poolerType = poolerType
self._poolerClass = _getPoolerClass(poolerType)
pArgTuples = _buildArgs(self._poolerClass, self, kwargs)
# include parent spatial pooler parameters
if poolerType == "union" or poolerType == "unionMonitored":
pArgTuplesSP = _buildArgs(_getParentSpatialPoolerClass(poolerType), self, kwargs)
# Make a list of automatic pooler arg names for later use
self._poolerArgNames = [t[0] for t in pArgTuples] + [t[0] for t in pArgTuplesSP]
else:
self._poolerArgNames = [t[0] for t in pArgTuples]
PyRegion.__init__(self, **kwargs)
# Defaults for all other parameters
self.learningMode = True
self.inferenceMode = True
self._inputWidth = inputWidth
self._columnCount = columnCount
self._historyLength = historyLength
self._minHistory = minHistory
# pooler instance
self._pooler = None
def __init__(self,
columnCount, # Number of columns in the SP, a required parameter
inputWidth, # Size of inputs to the SP, a required parameter
spatialImp=getDefaultSPImp(), #'py', 'cpp'
**kwargs):
if columnCount <= 0 or inputWidth <=0:
raise TypeError("Parameters columnCount and inputWidth must be > 0")
# Pull out the spatial arguments automatically
# These calls whittle down kwargs and create instance variables of SPRegion
self.SpatialClass = getSPClass(spatialImp)
sArgTuples = _buildArgs(self.SpatialClass.__init__, self, kwargs)
# Make a list of automatic spatial arg names for later use
self._spatialArgNames = [t[0] for t in sArgTuples]
# Learning and SP parameters.
# By default we start out in stage learn with inference disabled
self.learningMode = True
self.inferenceMode = False
self.anomalyMode = False
self.topDownMode = False
self.columnCount = columnCount
self.inputWidth = inputWidth
PyRegion.__init__(self, **kwargs)
# Initialize all non-persistent base members, as well as give
# derived class an opportunity to do the same.
self._loaded = False
self._initializeEphemeralMembers()
# Debugging support, used in _conditionalBreak
self.breakPdb = False
self.breakKomodo = False
# Defaults for all other parameters
self.logPathInput = ''
self.logPathOutput = ''
self.logPathOutputDense = ''
self._fpLogSPInput = None
self._fpLogSP = None
self._fpLogSPDense = None
#
# Variables set up in initInNetwork()
#
# Spatial instance
self._sfdr = None
# Spatial pooler's bottom-up output value: hang on to this output for
# top-down inference and for debugging
self._spatialPoolerOutput = None
# Spatial pooler's bottom-up input: hang on to this for supporting the
# spInputNonZeros parameter
self._spatialPoolerInput = None
def __init__(
self,
# Input sizes
columnCount,
basalInputWidth,
apicalInputWidth=0,
# TM params
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
reducedBasalThreshold=13, # ApicalTiebreak and ApicalDependent only
sampleSize=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
basalPredictedSegmentDecrement=0.0,
apicalPredictedSegmentDecrement=0.0,
learnOnOneCell=False, # ApicalTiebreakCPP only
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255, # ApicalTiebreakCPP only
seed=42,
# Region params
implementation="ApicalTiebreak",
learn=True,
**kwargs):
# Input sizes (the network API doesn't provide these during initialize)
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.reducedBasalThreshold = reducedBasalThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.sampleSize = sampleSize
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.basalPredictedSegmentDecrement = basalPredictedSegmentDecrement
self.apicalPredictedSegmentDecrement = apicalPredictedSegmentDecrement
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.maxSegmentsPerCell = maxSegmentsPerCell
self.learnOnOneCell = learnOnOneCell
self.seed = seed
# Region params
self.implementation = implementation
self.learn = learn
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self,
columnCount,
inputWidth,
spatialImp=getDefaultSPImp(),
**kwargs):
if columnCount <= 0 or inputWidth <=0:
raise TypeError("Parameters columnCount and inputWidth must be > 0")
# Pull out the spatial arguments automatically
# These calls whittle down kwargs and create instance variables of SPRegion
self.spatialImp = spatialImp
self.SpatialClass = getSPClass(spatialImp)
sArgTuples = _buildArgs(self.SpatialClass.__init__, self, kwargs)
# Make a list of automatic spatial arg names for later use
self._spatialArgNames = [t[0] for t in sArgTuples]
# Learning and SP parameters.
# By default we start out in stage learn with inference disabled
self.learningMode = True
self.inferenceMode = False
self.anomalyMode = False
self.topDownMode = False
self.columnCount = columnCount
self.inputWidth = inputWidth
PyRegion.__init__(self, **kwargs)
# Initialize all non-persistent base members, as well as give
# derived class an opportunity to do the same.
self._loaded = False
self._initializeEphemeralMembers()
# Debugging support, used in _conditionalBreak
self.breakPdb = False
self.breakKomodo = False
# Defaults for all other parameters
self.logPathInput = ''
self.logPathOutput = ''
self.logPathOutputDense = ''
self._fpLogSPInput = None
self._fpLogSP = None
self._fpLogSPDense = None
#
# Variables set up in initInNetwork()
#
# Spatial instance
self._sfdr = None
# Spatial pooler's bottom-up output value: hang on to this output for
# top-down inference and for debugging
self._spatialPoolerOutput = None
# Spatial pooler's bottom-up input: hang on to this for supporting the
# spInputNonZeros parameter
self._spatialPoolerInput = None
def __init__(self,
moduleCount,
cellsPerAxis,
scale,
orientation,
anchorInputSize,
activeFiringRate,
bumpSigma,
activationThreshold=10,
initialPermanence=0.21,
connectedPermanence=0.50,
learningThreshold=10,
sampleSize=20,
permanenceIncrement=0.1,
permanenceDecrement=0.0,
maxSynapsesPerSegment=-1,
bumpOverlapMethod="probabilistic",
learningMode=False,
seed=42,
dualPhase=True,
dimensions=2,
**kwargs):
if moduleCount <= 0 or cellsPerAxis <= 0:
raise TypeError("Parameters moduleCount and cellsPerAxis must be > 0")
if moduleCount != len(scale) or moduleCount != len(orientation):
raise TypeError("scale and orientation arrays len must match moduleCount")
if dimensions < 2:
raise TypeError("dimensions must be >= 2")
self.moduleCount = moduleCount
self.cellsPerAxis = cellsPerAxis
self.cellCount = cellsPerAxis * cellsPerAxis
self.scale = list(scale)
self.orientation = list(orientation)
self.anchorInputSize = anchorInputSize
self.activeFiringRate = activeFiringRate
self.bumpSigma = bumpSigma
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.learningThreshold = learningThreshold
self.sampleSize = sampleSize
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.bumpOverlapMethod = bumpOverlapMethod
self.learningMode = learningMode
self.dualPhase = dualPhase
self.dimensions = dimensions
self.seed = seed
# This flag controls whether the region is processing sensation or movement
# on dual phase configuration
self._sensing = False
self._modules = None
self._projection = None
PyRegion.__init__(self, **kwargs)
def __init__(self,
columnCount=2048,
cellsPerColumn=16,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
defaultOutputType="active",
**kwargs):
# Defaults for all other parameters
self.columnCount = columnCount
self.cellsPerColumn = cellsPerColumn
self.inputWidth = self.columnCount * self.cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learningMode = True
self.inferenceMode = True
self.defaultOutputType = defaultOutputType
PyRegion.__init__(self, **kwargs)
def __init__(self,
columnCount, # Number of columns in the SP, a required parameter
inputWidth, # Size of inputs to the SP, a required parameter
cellsPerColumn, # Number of cells per column, required
# Constructor arguments are picked up automatically. There is no
# need to add them anywhere in TMRegion, unless you need to do
# something special with them. See docstring above.
orColumnOutputs=False,
cellsSavePath='',
temporalImp=gDefaultTemporalImp,
anomalyMode=False,
computePredictedActiveCellIndices=False,
**kwargs):
# Which Temporal implementation?
TemporalClass = _getTPClass(temporalImp)
# Make a list of automatic temporal arg names for later use
# Pull out the temporal arguments automatically
# These calls whittle down kwargs and create instance variables of TMRegion
tArgTuples = _buildArgs(TemporalClass.__init__, self, kwargs)
self._temporalArgNames = [t[0] for t in tArgTuples]
self.learningMode = True # Start out with learning enabled
self.inferenceMode = False
self.anomalyMode = anomalyMode
self.computePredictedActiveCellIndices = computePredictedActiveCellIndices
self.topDownMode = False
self.columnCount = columnCount
self.inputWidth = inputWidth
self.outputWidth = columnCount * cellsPerColumn
self.cellsPerColumn = cellsPerColumn
PyRegion.__init__(self, **kwargs)
# Initialize all non-persistent base members, as well as give
# derived class an opportunity to do the same.
self._loaded = False
self._initialize()
# Debugging support, used in _conditionalBreak
self.breakPdb = False
self.breakKomodo = False
# TMRegion only, or special handling
self.orColumnOutputs = orColumnOutputs
self.temporalImp = temporalImp
# Various file names
self.storeDenseOutput = False
self.logPathOutput = ''
self.cellsSavePath = cellsSavePath
self._fpLogTPOutput = None
# Variables set up in initInNetwork()
self._tfdr = None # FDRTemporal instance
def __init__(self,
columnCount=2048,
cellsPerColumn=16,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
defaultOutputType = "active",
**kwargs):
# Defaults for all other parameters
self.columnCount = columnCount
self.cellsPerColumn = cellsPerColumn
self.inputWidth = self.columnCount*self.cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learningMode = True
self.inferenceMode = True
self.defaultOutputType = defaultOutputType
PyRegion.__init__(self, **kwargs)
def __init__(self,
# Modified ETM params
columnCount=2048,
basalInputWidth=0,
apicalInputWidth=0,
# ETM params
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
formInternalBasalConnections=True,
learnOnOneCell=False,
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255,
seed=42,
checkInputs=True,
# Region params
implementation="etm_cpp",
learn=True,
**kwargs):
# Input sizes (the network API doesn't provide these during initialize)
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.formInternalBasalConnections = formInternalBasalConnections
self.learnOnOneCell = learnOnOneCell
self.maxSegmentsPerCell = maxSegmentsPerCell
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.seed = seed
self.checkInputs = checkInputs
# Region params
self.implementation = implementation
self.learn = learn
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self,
# Input sizes
columnCount,
basalInputWidth,
apicalInputWidth=0,
# TM params
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
reducedBasalThreshold=13, # ApicalTiebreak and ApicalDependent only
sampleSize=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
basalPredictedSegmentDecrement=0.0,
apicalPredictedSegmentDecrement=0.0,
learnOnOneCell=False, # ApicalTiebreakCPP only
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255, # ApicalTiebreakCPP only
seed=42,
# Region params
implementation="ApicalTiebreak",
learn=True,
**kwargs):
# Input sizes (the network API doesn't provide these during initialize)
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.reducedBasalThreshold = reducedBasalThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.sampleSize = sampleSize
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.basalPredictedSegmentDecrement = basalPredictedSegmentDecrement
self.apicalPredictedSegmentDecrement = apicalPredictedSegmentDecrement
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.maxSegmentsPerCell = maxSegmentsPerCell
self.learnOnOneCell = learnOnOneCell
self.seed = seed
# Region params
self.implementation = implementation
self.learn = learn
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self,
moduleCount,
cellsPerAxis,
scale,
orientation,
anchorInputSize,
activeFiringRate,
bumpSigma,
activationThreshold=10,
initialPermanence=0.21,
connectedPermanence=0.50,
learningThreshold=10,
sampleSize=20,
permanenceIncrement=0.1,
permanenceDecrement=0.0,
maxSynapsesPerSegment=-1,
bumpOverlapMethod="probabilistic",
learningMode=False,
seed=42,
dualPhase=True,
**kwargs):
if moduleCount <= 0 or cellsPerAxis <= 0:
raise TypeError(
"Parameters moduleCount and cellsPerAxis must be > 0")
if moduleCount != len(scale) or moduleCount != len(orientation):
raise TypeError(
"scale and orientation arrays len must match moduleCount")
self.moduleCount = moduleCount
self.cellsPerAxis = cellsPerAxis
self.cellCount = cellsPerAxis * cellsPerAxis
self.scale = list(scale)
self.orientation = list(orientation)
self.anchorInputSize = anchorInputSize
self.activeFiringRate = activeFiringRate
self.bumpSigma = bumpSigma
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.learningThreshold = learningThreshold
self.sampleSize = sampleSize
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.bumpOverlapMethod = bumpOverlapMethod
self.learningMode = learningMode
self.dualPhase = dualPhase
self.seed = seed
# This flag controls whether the region is processing sensation or movement
# on dual phase configuration
self._sensing = False
self._modules = None
PyRegion.__init__(self, **kwargs)
def __init__(self,
cellCount=4096,
inputWidth=16384,
numOtherCorticalColumns=0,
sdrSize=40,
# Proximal
synPermProximalInc=0.1,
synPermProximalDec=0.001,
initialProximalPermanence=0.6,
sampleSizeProximal=20,
minThresholdProximal=1,
connectedPermanenceProximal=0.50,
# Distal
synPermDistalInc=0.10,
synPermDistalDec=0.10,
initialDistalPermanence=0.21,
sampleSizeDistal=20,
activationThresholdDistal=13,
connectedPermanenceDistal=0.50,
distalSegmentInhibitionFactor=1.5,
seed=42,
defaultOutputType = "active",
**kwargs):
# Used to derive Column Pooler params
self.numOtherCorticalColumns = numOtherCorticalColumns
# Column Pooler params
self.inputWidth = inputWidth
self.cellCount = cellCount
self.sdrSize = sdrSize
self.synPermProximalInc = synPermProximalInc
self.synPermProximalDec = synPermProximalDec
self.initialProximalPermanence = initialProximalPermanence
self.sampleSizeProximal = sampleSizeProximal
self.minThresholdProximal = minThresholdProximal
self.connectedPermanenceProximal = connectedPermanenceProximal
self.synPermDistalInc = synPermDistalInc
self.synPermDistalDec = synPermDistalDec
self.initialDistalPermanence = initialDistalPermanence
self.sampleSizeDistal = sampleSizeDistal
self.activationThresholdDistal = activationThresholdDistal
self.connectedPermanenceDistal = connectedPermanenceDistal
self.distalSegmentInhibitionFactor = distalSegmentInhibitionFactor
self.seed = seed
# Region params
self.learningMode = True
self.defaultOutputType = defaultOutputType
self._pooler = None
PyRegion.__init__(self, **kwargs)
def __init__(
self,
cellCount=4096,
inputWidth=16384,
numOtherCorticalColumns=0,
sdrSize=40,
# Proximal
synPermProximalInc=0.1,
synPermProximalDec=0.001,
initialProximalPermanence=0.6,
sampleSizeProximal=20,
minThresholdProximal=1,
connectedPermanenceProximal=0.50,
# Distal
synPermDistalInc=0.10,
synPermDistalDec=0.10,
initialDistalPermanence=0.21,
sampleSizeDistal=20,
activationThresholdDistal=13,
connectedPermanenceDistal=0.50,
distalSegmentInhibitionFactor=1.5,
seed=42,
defaultOutputType="active",
**kwargs):
# Used to derive Column Pooler params
self.numOtherCorticalColumns = numOtherCorticalColumns
# Column Pooler params
self.inputWidth = inputWidth
self.cellCount = cellCount
self.sdrSize = sdrSize
self.synPermProximalInc = synPermProximalInc
self.synPermProximalDec = synPermProximalDec
self.initialProximalPermanence = initialProximalPermanence
self.sampleSizeProximal = sampleSizeProximal
self.minThresholdProximal = minThresholdProximal
self.connectedPermanenceProximal = connectedPermanenceProximal
self.synPermDistalInc = synPermDistalInc
self.synPermDistalDec = synPermDistalDec
self.initialDistalPermanence = initialDistalPermanence
self.sampleSizeDistal = sampleSizeDistal
self.activationThresholdDistal = activationThresholdDistal
self.connectedPermanenceDistal = connectedPermanenceDistal
self.distalSegmentInhibitionFactor = distalSegmentInhibitionFactor
self.seed = seed
# Region params
self.learningMode = True
self.defaultOutputType = defaultOutputType
self._pooler = None
PyRegion.__init__(self, **kwargs)
def __init__(self,
columnCount=2048,
inputWidth=16384,
lateralInputWidth=0,
activationThresholdDistal=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThresholdProximal=1,
minThresholdDistal=10,
maxNewProximalSynapseCount=20,
maxNewDistalSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
synPermProximalInc=0.1,
synPermProximalDec=0.001,
initialProximalPermanence = 0.6,
seed=42,
numActiveColumnsPerInhArea=40,
defaultOutputType = "active",
**kwargs):
# Modified Column Pooler params
self.columnCount = columnCount
# Column Pooler params
self.inputWidth = inputWidth
self.lateralInputWidth = lateralInputWidth
self.activationThresholdDistal = activationThresholdDistal
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThresholdProximal = minThresholdProximal
self.minThresholdDistal = minThresholdDistal
self.maxNewProximalSynapseCount = maxNewProximalSynapseCount
self.maxNewDistalSynapseCount = maxNewDistalSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.synPermProximalInc = synPermProximalInc
self.synPermProximalDec = synPermProximalDec
self.initialProximalPermanence = initialProximalPermanence
self.seed = seed
self.numActiveColumnsPerInhArea = numActiveColumnsPerInhArea
self.maxSynapsesPerSegment = inputWidth
# Region params
self.learningMode = True
self.inferenceMode = True
self.defaultOutputType = defaultOutputType
self._pooler = None
PyRegion.__init__(self, **kwargs)
def __init__(self,
columnCount=2048,
inputWidth=16384,
lateralInputWidth=0,
activationThresholdDistal=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThresholdProximal=1,
minThresholdDistal=10,
maxNewProximalSynapseCount=20,
maxNewDistalSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
synPermProximalInc=0.1,
synPermProximalDec=0.001,
initialProximalPermanence=0.6,
seed=42,
numActiveColumnsPerInhArea=40,
defaultOutputType="active",
**kwargs):
# Modified Column Pooler params
self.columnCount = columnCount
# Column Pooler params
self.inputWidth = inputWidth
self.lateralInputWidth = lateralInputWidth
self.activationThresholdDistal = activationThresholdDistal
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThresholdProximal = minThresholdProximal
self.minThresholdDistal = minThresholdDistal
self.maxNewProximalSynapseCount = maxNewProximalSynapseCount
self.maxNewDistalSynapseCount = maxNewDistalSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.synPermProximalInc = synPermProximalInc
self.synPermProximalDec = synPermProximalDec
self.initialProximalPermanence = initialProximalPermanence
self.seed = seed
self.numActiveColumnsPerInhArea = numActiveColumnsPerInhArea
self.maxSynapsesPerSegment = inputWidth
# Region params
self.learningMode = True
self.inferenceMode = True
self.defaultOutputType = defaultOutputType
self._pooler = None
PyRegion.__init__(self, **kwargs)
def __init__(self,
# Input sizes
columnCount,
basalInputWidth,
apicalInputWidth=0,
# TM params
cellsPerColumn=32,
minThreshold=0.5,
sampleSize=20,
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255,
seed=42,
noise=0.01, # lambda
learningRate=0.1, # alpha
initMovingAverages=0.0, # alpha
useApicalTiebreak=False,
# Region params
implementation="BayesianApicalTiebreak",
learn=True,
**kwargs):
# Input sizes (the network API doesn't provide these during initialize)
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.minThreshold = minThreshold
self.sampleSize = sampleSize
self.maxSegmentsPerCell = maxSegmentsPerCell
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.seed = seed
self.noise = noise
self.learningRate = learningRate
self.initMovingAverages = initMovingAverages
self.useApicalTiebreak = useApicalTiebreak
# Region params
self.implementation = implementation
self.learn = learn
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self,
columnCount=2048,
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
learnOnOneCell=1,
formInternalConnections=1,
formInternalBasalConnections=1,
defaultOutputType = "active",
monitor=False,
implementation="cpp",
**kwargs):
# Defaults for all other parameters
self.columnCount = columnCount
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learnOnOneCell = bool(learnOnOneCell)
self.learningMode = True
self.inferenceMode = True
self.formInternalConnections = bool(formInternalConnections)
self.formInternalBasalConnections = bool(formInternalBasalConnections)
self.defaultOutputType = defaultOutputType
self.monitor = monitor
self.implementation = implementation
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self,
verbosity=0,
colorOption=False,
colorDiscreteIntensity=5,
**kwargs):
self._colorOption = colorOption
self._colorDiscreteIntensity = colorDiscreteIntensity
self.dataSource = None
self.verbosity = verbosity
self._inputWidth = 768 * 1024 * 3
# fixed universe input
self._dataWidth = 160 * 160 * 3 * 5 if colorOption else 160 * 160
# output size dependent on color option
# lastRecord is the last record returned. Used for debugging only
self.lastRecord = None
PyRegion.__init__(self, **kwargs)
def __init__(self,
columnDimensions=(2048,),
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
learnOnOneCell=False,
tmImp=getDefaultTMImp(),
**kwargs):
# Pull out the tm arguments automatically
# These calls whittle down kwargs and create instance variables of TMRegion
self._tmClass = getTMClass(tmImp)
tmArgTuples = _buildArgs(self._tmClass, self, kwargs)
# Make a list of automatic tm arg names for later use
self._tmArgNames = [t[0] for t in tmArgTuples]
# Defaults for all other parameters
self.columnDimensions = copy.deepcopy(columnDimensions)
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learnOnOneCell = learnOnOneCell
self.learningMode = True
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self,
columnDimensions=(2048, ),
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
learnOnOneCell=False,
tmImp=getDefaultTMImp(),
**kwargs):
# Pull out the tm arguments automatically
# These calls whittle down kwargs and create instance variables of TMRegion
self._tmClass = getTMClass(tmImp)
tmArgTuples = _buildArgs(self._tmClass, self, kwargs)
# Make a list of automatic tm arg names for later use
self._tmArgNames = [t[0] for t in tmArgTuples]
# Defaults for all other parameters
self.columnDimensions = copy.deepcopy(columnDimensions)
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learnOnOneCell = learnOnOneCell
self.learningMode = True
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self,
columnCount=2048,
inputWidth=16384,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
synPermProximalInc=0.1,
synPermProximalDec=0.001,
initialProximalPermanence = 0.6,
seed=42,
numActiveColumnsPerInhArea=40,
defaultOutputType = "active",
**kwargs):
# Defaults for all other parameters
self.columnCount = columnCount
self.inputWidth = inputWidth
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.synPermProximalInc = synPermProximalInc
self.synPermProximalDec = synPermProximalDec
self.initialProximalPermanence = initialProximalPermanence
self.seed = seed
self.learningMode = True
self.inferenceMode = True
self.defaultOutputType = defaultOutputType
self.numActiveColumnsPerInhArea = numActiveColumnsPerInhArea
self._pooler = None
PyRegion.__init__(self, **kwargs)
def __init__(self,
columnCount=2048,
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
learnOnOneCell=1,
temporalImp="tm",
formInternalConnections=1,
defaultOutputType="active",
**kwargs):
# Defaults for all other parameters
self.columnCount = columnCount
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learnOnOneCell = bool(learnOnOneCell)
self.learningMode = True
self.inferenceMode = True
self.temporalImp = temporalImp
self.formInternalConnections = bool(formInternalConnections)
self.defaultOutputType = defaultOutputType
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self,
columnCount=2048,
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
learnOnOneCell=1,
temporalImp="tm",
formInternalConnections = 1,
**kwargs):
# Defaults for all other parameters
self.columnCount = columnCount
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learnOnOneCell = bool(learnOnOneCell)
self.learningMode = True
self.inferenceMode = True
self.temporalImp = temporalImp
self.formInternalConnections = bool(formInternalConnections)
self.previouslyPredictedCells = set()
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(
self,
# Modified ETM params
columnCount=2048,
basalInputWidth=0,
apicalInputWidth=0,
TDTraceDecay=0.0,
TDDiscount=0.0,
TDLearningRate=0.1,
globalValueDecay=0.0,
# ETM params
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
formInternalBasalConnections=True,
learnOnOneCell=False,
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255,
seed=42,
checkInputs=True,
# Region params
implementation="etm",
learn=True,
**kwargs):
# Input sizes (the network API doesn't provide these during initialize)
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.formInternalBasalConnections = formInternalBasalConnections
self.learnOnOneCell = learnOnOneCell
self.maxSegmentsPerCell = maxSegmentsPerCell
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.seed = seed
self.checkInputs = checkInputs
# Region params
self.implementation = implementation
self.learn = learn
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
# Reinforcement Learning variables (Eligability traces and values for each neuron)
self.TDDiscount = TDDiscount
self.TDLearningRate = TDLearningRate
self.TDTraceDecay = TDTraceDecay
self.globalValueDecay = globalValueDecay
self.traces = np.zeros(columnCount * cellsPerColumn)
self.values = np.zeros(columnCount * cellsPerColumn)
self.stateValue = 0
self.prevActiveCells = []
# Save prev. distal input for calculation with L5(t-1) distal input
self.prevActiveCellsExternalBasal = []
# For Debug save errors
self.TDError = 0
def __init__(
self,
# Modified TM params
columnCount=2048,
basalInputWidth=0,
apicalInputWidth=0,
# ETM params
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
formInternalBasalConnections=True,
learnOnOneCell=False,
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255,
seed=42,
checkInputs=True,
# Region params
defaultOutputType="active",
implementation="etm_cpp",
learningMode=True,
inferenceMode=True,
**kwargs
):
# Modified TM params
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.formInternalBasalConnections = formInternalBasalConnections
self.learnOnOneCell = learnOnOneCell
self.maxSegmentsPerCell = maxSegmentsPerCell
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.seed = seed
self.checkInputs = checkInputs
# Region params
self.defaultOutputType = defaultOutputType
self.implementation = implementation
self.learningMode = learningMode
self.inferenceMode = inferenceMode
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self, maxActive, outputWidth, **kwargs):
PyRegion.__init__(self, **kwargs)
self.maxActive = maxActive
self.outputWidth = outputWidth
def __init__(
self,
# Modified ETM params
columnCount=2048,
basalInputWidth=0,
apicalInputWidth=0,
# ETM params
cellsPerColumn=32,
initialPermanence=0.21,
connectedPermanence=0.50,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
maxSynapsesPerSegment=255,
seed=42,
sampleSize=20,
# apical, basal weighting
activationThresholdBasal=13,
activationThresholdApical=2,
minThresholdBasal=10,
minThresholdApical=1,
basalPredictedSegmentDecrement=0.001,
apicalPredictedSegmentDecrement=0.001,
# Region params
implementation="etm",
learn=True,
**kwargs):
# Input sizes (the network API doesn't provide these during initialize)
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.seed = seed
self.sampleSize = sampleSize
# TM weight distal and apical differently
self.minThresholdBasal = minThresholdBasal
self.minThresholdApical = minThresholdApical
self.activationThresholdBasal = activationThresholdBasal
self.activationThresholdApical = activationThresholdApical
self.basalPredictedSegmentDecrement = basalPredictedSegmentDecrement
self.apicalPredictedSegmentDecrement = apicalPredictedSegmentDecrement
# Region params
self.implementation = implementation
self.learn = learn
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
# Custom use internal activation t-1 as basal input
self.prevActivation = np.array([])
def __init__(self, maxActive, outputWidth, **kwargs):
PyRegion.__init__(self, **kwargs)
self.maxActive = maxActive
self.outputWidth = outputWidth
def __init__(self,
cellCount=4096,
inputWidth=16384,
numOtherCorticalColumns=0,
sdrSize=40,
maxSdrSize = None,
minSdrSize = None,
# Proximal
sampleSizeProximal=20,
# Distal
sampleSizeDistal=20,
inertiaFactor=1.,
# Bayesian
noise=0.01, # lambda
learningRate=0.1, # alpha
activationThreshold=0.5, # probability such that a cell becomes active
forgetting=0.1,
initMovingAverages=0.0,
useSupport=False,
avoidWeightExplosion=True,
resetProximalCounter=False,
useProximalProbabilities=True,
implementation="Bayesian",
seed=42,
defaultOutputType = "active",
**kwargs):
# Used to derive Column Pooler params
self.numOtherCorticalColumns = numOtherCorticalColumns
# Column Pooler params
self.inputWidth = inputWidth
self.cellCount = cellCount
self.sdrSize = sdrSize
self.maxSdrSize = maxSdrSize
self.minSdrSize = minSdrSize
self.sampleSizeProximal = sampleSizeProximal
self.sampleSizeDistal = sampleSizeDistal
self.inertiaFactor = inertiaFactor
self.seed = seed
self.activationThreshold = activationThreshold
self.learningRate = learningRate
self.noise = noise
self.implementation = implementation
self.forgetting = forgetting
self.initMovingAverages = initMovingAverages
self.useSupport = useSupport
self.avoidWeightExplosion = avoidWeightExplosion
self.resetProximalCounter = resetProximalCounter
self.useProximalProbabilities = useProximalProbabilities
# Region params
self.learningMode = True
self.defaultOutputType = defaultOutputType
self._pooler = None
PyRegion.__init__(self, **kwargs)
def __init__(
self,
# Modified TM params
columnCount=2048,
basalInputWidth=0,
apicalInputWidth=0,
# ETM params
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
formInternalBasalConnections=True,
learnOnOneCell=False,
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255,
seed=42,
checkInputs=True,
# Region params
defaultOutputType="active",
implementation="etm",
learningMode=True,
inferenceMode=True,
**kwargs):
# Modified TM params
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.formInternalBasalConnections = formInternalBasalConnections
self.learnOnOneCell = learnOnOneCell
self.maxSegmentsPerCell = maxSegmentsPerCell
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.seed = seed
self.checkInputs = checkInputs
# Region params
self.defaultOutputType = defaultOutputType
self.implementation = implementation
self.learningMode = learningMode
self.inferenceMode = inferenceMode
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(
self,
# Modified TM params
basalInputWidth=0,
apicalInputWidth=0,
apicalGlobalDecay=0.000001,
TDLearningRate=0.5,
winnerSize=4,
motorCount=32,
synPermActiveIncMotor=0.04,
synPermInactiveDecMotor=0.008,
# TM params
columnCount=2048,
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
punishPredDec=0.0,
maxSynapsesPerSegment=255,
seed=42,
# Region params
learn=True,
**kwargs):
# Input sizes (the network API doesn't provide these during initialize)
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.columnCount = columnCount
self.cellsPerColumn = cellsPerColumn
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.seed = seed
# Motor specific
self.TDLearningRate = TDLearningRate
self.apicalGlobalDecay = apicalGlobalDecay
self.winnerSize = winnerSize
self.punishPredDec = punishPredDec
self.motorCount = motorCount
self.synPermActiveIncMotor = synPermActiveIncMotor
self.synPermInactiveDecMotor = synPermInactiveDecMotor
# Region params
self.learn = learn
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None