def _adaptSegment(connections, segment, prevActiveCells, permanenceIncrement,
permanenceDecrement):
"""
Updates synapses on segment.
Strengthens active synapses; weakens inactive synapses.
@param connections (Object) Connections instance for the tm
@param segment (int) Segment to adapt
@param prevActiveCells (list) Active cells in `t-1`
@param permanenceIncrement (float) Amount to increment active synapses
@param permanenceDecrement (float) Amount to decrement inactive synapses
"""
for synapse in connections.synapsesForSegment(segment):
permanence = synapse.permanence
if binSearch(prevActiveCells, synapse.presynapticCell) != -1:
permanence += permanenceIncrement
else:
permanence -= permanenceDecrement
# Keep permanence within min/max bounds
permanence = max(0.0, min(1.0, permanence))
if permanence < EPSILON:
connections.destroySynapse(synapse)
else:
connections.updateSynapsePermanence(synapse, permanence)
if connections.numSynapses(segment) == 0:
connections.destroySegment(segment)
def _growSynapses(cls, connections, random, segment, nDesiredNewSynapes,
prevWinnerCells, initialPermanence):
"""
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.
@param connections (Object) Connections instance for the tm
@param random (Object) TM object used to generate random
numbers
@param segment (int) Segment to grow synapses on.
@params nDesiredNewSynapes (int) Desired number of synapses to grow
@params prevWinnerCells (list) Winner cells in `t-1`
@param initialPermanence (float) Initial permanence of a new synapse.
"""
candidates = list(prevWinnerCells)
for synapse in connections.synapsesForSegment(segment):
i = binSearch(candidates, synapse.presynapticCell)
if i != -1:
del candidates[i]
nActual = min(nDesiredNewSynapes, len(candidates))
for _ in range(nActual):
i = random.getUInt32(len(candidates))
connections.createSynapse(segment, candidates[i],
initialPermanence)
del candidates[i]
def _growSynapses(cls, connections, random, segment, nDesiredNewSynapes,
prevWinnerCells, initialPermanence):
"""
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.
@param connections (Object) Connections instance for the tm
@param random (Object) TM object used to generate random
numbers
@param segment (int) Segment to grow synapses on.
@params nDesiredNewSynapes (int) Desired number of synapses to grow
@params prevWinnerCells (list) Winner cells in `t-1`
@param initialPermanence (float) Initial permanence of a new synapse.
"""
candidates = list(prevWinnerCells)
for synapse in connections.synapsesForSegment(segment):
i = binSearch(candidates, synapse.presynapticCell)
if i != -1:
del candidates[i]
nActual = min(nDesiredNewSynapes, len(candidates))
for _ in range(nActual):
i = random.getUInt32(len(candidates))
connections.createSynapse(segment, candidates[i], initialPermanence)
del candidates[i]
def adaptSegment(cls, connections, segment, prevActiveCells,
permanenceIncrement, permanenceDecrement):
""" Updates synapses on segment.
Strengthens active synapses; weakens inactive synapses.
@param connections (Object) Connections instance for the tm
@param segment (int) Segment to adapt
@param prevActiveCells (list) Active cells in `t-1`
@param permanenceIncrement (float) Amount to increment active synapses
@param permanenceDecrement (float) Amount to decrement inactive synapses
"""
for synapse in connections.synapsesForSegment(segment):
permanence = synapse.permanence
if binSearch(prevActiveCells, synapse.presynapticCell) != -1:
permanence += permanenceIncrement
else:
permanence -= permanenceDecrement
# Keep permanence within min/max bounds
permanence = max(0.0, min(1.0, permanence))
if permanence < EPSILON:
connections.destroySynapse(synapse)
else:
connections.updateSynapsePermanence(synapse, permanence)
if connections.numSynapses(segment) == 0:
connections.destroySegment(segment)
def _adaptSegment(cls, connections, segment,
reinforceCandidatesInternal, reinforceCandidatesExternal,
permanenceIncrement, permanenceDecrement):
numCells = connections.numCells
# Destroying a synapse modifies the set that we're iterating through.
synapsesToDestroy = []
for synapse in connections.synapsesForSegment(segment):
permanence = synapse.permanence
presynapticCell = synapse.presynapticCell
if presynapticCell < numCells:
isActive = -1 != binSearch(reinforceCandidatesInternal,
presynapticCell)
else:
isActive = -1 != binSearch(reinforceCandidatesExternal,
presynapticCell - numCells)
if isActive:
permanence += permanenceIncrement
else:
permanence -= permanenceDecrement
# Keep permanence within min/max bounds.
permanence = max(0.0, min(1.0, permanence))
if permanence < EPSILON:
synapsesToDestroy.append(synapse)
else:
connections.updateSynapsePermanence(synapse, permanence)
for synapse in synapsesToDestroy:
connections.destroySynapse(synapse)
if connections.numSynapses(segment) == 0:
connections.destroySegment(segment)
def _growSynapses(cls, connections, rng, segment, nDesiredNewSynapes,
growthCandidatesInternal, growthCandidatesExternal,
initialPermanence):
numCells = connections.numCells
candidates = list(growthCandidatesInternal)
candidates.extend(cell + numCells for cell in growthCandidatesExternal)
for synapse in connections.synapsesForSegment(segment):
i = binSearch(candidates, synapse.presynapticCell)
if i != -1:
del candidates[i]
nActual = min(nDesiredNewSynapes, len(candidates))
for _ in range(nActual):
i = rng.getUInt32(len(candidates))
connections.createSynapse(segment, candidates[i], initialPermanence)
del candidates[i]
