def testMaxSegmentsPerCellGetter(self):
tm = TemporalMemory(
columnDimensions=[64,64],
cellsPerColumn=32,
maxSegmentsPerCell=200
)
self.assertEqual(tm.getMaxSegmentsPerCell(), 200)
def testComputePredictiveCells(self):
tm = TemporalMemory(activationThreshold=2,
minThreshold=2,
predictedSegmentDecrement=0.004)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
connections.createSynapse(0, 37, 0.5)
connections.createSynapse(0, 477, 0.9)
connections.createSegment(1)
connections.createSynapse(1, 733, 0.7)
connections.createSynapse(1, 733, 0.4)
connections.createSegment(1)
connections.createSynapse(2, 974, 0.9)
connections.createSegment(8)
connections.createSynapse(3, 486, 0.9)
connections.createSegment(100)
activeCells = set([23, 37, 733, 974])
(activeSegments, predictiveCells, matchingSegments,
matchingCells) = tm.computePredictiveCells(activeCells, connections)
self.assertEqual(activeSegments, set([0]))
self.assertEqual(predictiveCells, set([0]))
self.assertEqual(matchingSegments, set([0, 1]))
self.assertEqual(matchingCells, set([0, 1]))
def testMaxSynapsesPerSegmentGetter(self):
tm = TemporalMemory(
columnDimensions=[32,32],
cellsPerColumn=16,
maxSynapsesPerSegment=150
)
self.assertEqual(tm.getMaxSynapsesPerSegment(), 150)
def testBestMatchingSegment(self):
tm = TemporalMemory(
connectedPermanence=0.50,
minThreshold=1
)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
connections.createSynapse(0, 37, 0.4)
connections.createSynapse(0, 477, 0.9)
connections.createSegment(0)
connections.createSynapse(1, 49, 0.9)
connections.createSynapse(1, 3, 0.8)
connections.createSegment(1)
connections.createSynapse(2, 733, 0.7)
connections.createSegment(8)
connections.createSynapse(3, 486, 0.9)
activeCells = set([23, 37, 49, 733])
self.assertEqual(tm.bestMatchingSegment(0, activeCells), (0, 2))
self.assertEqual(tm.bestMatchingSegment(1, activeCells), (2, 1))
self.assertEqual(tm.bestMatchingSegment(8, activeCells), (None, None))
self.assertEqual(tm.bestMatchingSegment(100, activeCells), (None, None))
def testComputePredictiveCells(self):
tm = TemporalMemory(activationThreshold=2,
minThreshold=2,
predictedSegmentDecrement=0.004)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
connections.createSynapse(0, 37, 0.5)
connections.createSynapse(0, 477, 0.9)
connections.createSegment(1)
connections.createSynapse(1, 733, 0.7)
connections.createSynapse(1, 733, 0.4)
connections.createSegment(1)
connections.createSynapse(2, 974, 0.9)
connections.createSegment(8)
connections.createSynapse(3, 486, 0.9)
connections.createSegment(100)
activeCells = set([23, 37, 733, 974])
(activeSegments,
predictiveCells,
matchingSegments,
matchingCells) = tm.computePredictiveCells(activeCells)
self.assertEqual(activeSegments, set([0]))
self.assertEqual(predictiveCells, set([0]))
self.assertEqual(matchingSegments, set([0,1]))
self.assertEqual(matchingCells, set([0,1]))
def testDestroyWeakSynapseOnWrongPrediction(self):
tm = TemporalMemory(
columnDimensions=[32],
cellsPerColumn=4,
activationThreshold=3,
initialPermanence=.2,
connectedPermanence=.50,
minThreshold=2,
maxNewSynapseCount=4,
permanenceIncrement=.10,
permanenceDecrement=.10,
predictedSegmentDecrement=0.02,
seed=42)
previousActiveColumns = [0]
previousActiveCells = [0, 1, 2, 3]
activeColumns = [2]
expectedActiveCells = [5]
activeSegment = tm.connections.createSegment(expectedActiveCells[0])
tm.connections.createSynapse(activeSegment, previousActiveCells[0], .5)
tm.connections.createSynapse(activeSegment, previousActiveCells[1], .5)
tm.connections.createSynapse(activeSegment, previousActiveCells[2], .5)
weakActiveSynapse = tm.connections.createSynapse(activeSegment,
previousActiveCells[3],
.015)
tm.compute(previousActiveColumns, True)
tm.compute(activeColumns, True)
self.assertTrue(tm.connections.dataForSynapse(weakActiveSynapse).destroyed)
def testMaxSegmentsPerCellGetter(self):
tm = TemporalMemory(
columnDimensions=[64,64],
cellsPerColumn=32,
maxSegmentsPerCell=200
)
self.assertEqual(tm.getMaxSegmentsPerCell(), 200)
def testNoGrowthOnCorrectlyActiveSegments(self):
tm = TemporalMemory(
columnDimensions=[32],
cellsPerColumn=4,
activationThreshold=3,
initialPermanence=.2,
connectedPermanence=.50,
minThreshold=2,
maxNewSynapseCount=3,
permanenceIncrement=.10,
permanenceDecrement=.10,
predictedSegmentDecrement=0.02,
seed=42)
previousActiveColumns = [0]
previousActiveCells = [0,1,2,3]
activeColumns = [1]
activeCell = 5
activeSegment = tm.connections.createSegment(activeCell)
tm.connections.createSynapse(activeSegment, previousActiveCells[0], .5)
tm.connections.createSynapse(activeSegment, previousActiveCells[1], .5)
tm.connections.createSynapse(activeSegment, previousActiveCells[2], .5)
tm.compute(previousActiveColumns, True)
tm.compute(activeColumns, True)
self.assertEqual(3, len(tm.connections.synapsesForSegment(activeSegment)))
def testCellsForColumn2D(self):
tm = TemporalMemory(
columnDimensions=[64, 64],
cellsPerColumn=4
)
expectedCells = set([256, 257, 258, 259])
self.assertEqual(tm.cellsForColumn(64), expectedCells)
def testComputePredictiveCells(self):
tm = TemporalMemory(activationThreshold=2)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
connections.createSynapse(0, 37, 0.5)
connections.createSynapse(0, 477, 0.9)
connections.createSegment(1)
connections.createSynapse(1, 733, 0.7)
connections.createSynapse(1, 733, 0.4)
connections.createSegment(1)
connections.createSynapse(2, 974, 0.9)
connections.createSegment(8)
connections.createSynapse(3, 486, 0.9)
connections.createSegment(100)
activeCells = set([23, 37, 733, 974])
(activeSegments, predictiveCells,
numActiveSynapsesForSegment) = tm.computePredictiveCells(
activeCells, connections)
self.assertEqual(activeSegments, set([0]))
self.assertEqual(predictiveCells, set([0]))
self.assertEqual(numActiveSynapsesForSegment, {0: 2, 1: 2, 2: 1})
def testCellsForColumn1D(self):
tm = TemporalMemory(
columnDimensions=[2048],
cellsPerColumn=5
)
expectedCells = set([5, 6, 7, 8, 9])
self.assertEqual(tm.cellsForColumn(1), expectedCells)
def __init__(self, config):
# Calculate the size of input and col space
inputsize = np.array(config['inputDimensions']).prod()
colsize = np.array(config['columnDimensions']).prod()
# save colsize and data type
self.colsize = colsize
self.datatype = config['uintType']
self.numIterations = config['numIterations']
# setup the pooler and reference to active column holder
self.sp = SpatialPooler(
inputDimensions=config['inputDimensions'],
columnDimensions=config['columnDimensions'],
potentialRadius=int(config['potentialRadius'] * inputsize),
numActiveColumnsPerInhArea=math.ceil(
config['amountActiveCols'] * colsize),
globalInhibition=config['inhibition']
)
# reference to active columns set that is output of the spatial pooler
self.activeColumns = np.zeros(colsize, config['uintType'])
# setup the temporal pooler
self.tm = TemporalMemory(
columnDimensions=config['columnDimensions'],
cellsPerColumn=config['cellsPerColumn']
)
def testMaxSynapsesPerSegmentGetter(self):
tm = TemporalMemory(
columnDimensions=[32,32],
cellsPerColumn=16,
maxSynapsesPerSegment=150
)
self.assertEqual(tm.getMaxSynapsesPerSegment(), 150)
def testWriteRead(self):
tm1 = TemporalMemory(columnDimensions=(32, ),
cellsPerColumn=4,
activationThreshold=3,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=2,
maxNewSynapseCount=3,
permanenceIncrement=0.1,
permanenceDecrement=0.1,
predictedSegmentDecrement=0.0,
seed=42)
self.serializationTestPrepare(tm1)
proto1 = TemporalMemoryProto_capnp.TemporalMemoryProto.new_message()
tm1.write(proto1)
# Write the proto to a temp file and read it back into a new proto
with tempfile.TemporaryFile() as f:
proto1.write(f)
f.seek(0)
proto2 = TemporalMemoryProto_capnp.TemporalMemoryProto.read(f)
# Load the deserialized proto
tm2 = TemporalMemory.read(proto2)
self.assertEqual(tm1, tm2)
self.serializationTestVerify(tm2)
def testComputePredictiveCells(self):
tm = TemporalMemory(activationThreshold=2)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
connections.createSynapse(0, 37, 0.5)
connections.createSynapse(0, 477, 0.9)
connections.createSegment(1)
connections.createSynapse(1, 733, 0.7)
connections.createSynapse(1, 733, 0.4)
connections.createSegment(1)
connections.createSynapse(2, 974, 0.9)
connections.createSegment(8)
connections.createSynapse(3, 486, 0.9)
connections.createSegment(100)
activeSynapsesForSegment = {0: set([0, 1]),
1: set([3, 4]),
2: set([5])}
(activeSegments,
predictiveCells) = tm.computePredictiveCells(activeSynapsesForSegment,
connections)
self.assertEqual(activeSegments, set([0]))
self.assertEqual(predictiveCells, set([0]))
def testDestroySegmentsWithTooFewSynapsesToBeMatching(self):
tm = TemporalMemory(
columnDimensions=[32],
cellsPerColumn=4,
activationThreshold=3,
initialPermanence=.2,
connectedPermanence=.50,
minThreshold=2,
maxNewSynapseCount=4,
permanenceIncrement=.10,
permanenceDecrement=.10,
predictedSegmentDecrement=0.02,
seed=42)
prevActiveColumns = [0]
prevActiveCells = [0, 1, 2, 3]
activeColumns = [2]
expectedActiveCell = 5
matchingSegment = tm.connections.createSegment(expectedActiveCell)
tm.connections.createSynapse(matchingSegment, prevActiveCells[0], .015)
tm.connections.createSynapse(matchingSegment, prevActiveCells[1], .015)
tm.connections.createSynapse(matchingSegment, prevActiveCells[2], .015)
tm.connections.createSynapse(matchingSegment, prevActiveCells[3], .015)
tm.compute(prevActiveColumns, True)
tm.compute(activeColumns, True)
self.assertEqual(0, tm.connections.numSegments(expectedActiveCell))
def testDestroyWeakSynapseOnActiveReinforce(self):
tm = TemporalMemory(
columnDimensions=[32],
cellsPerColumn=4,
activationThreshold=3,
initialPermanence=.2,
connectedPermanence=.50,
minThreshold=2,
maxNewSynapseCount=4,
permanenceIncrement=.10,
permanenceDecrement=.10,
predictedSegmentDecrement=0.02,
seed=42)
previousActiveColumns = [0]
previousActiveCells = [0, 1, 2, 3]
activeColumns = [2]
activeCell = 5
activeSegment = tm.connections.createSegment(activeCell)
tm.connections.createSynapse(activeSegment, previousActiveCells[0], .5)
tm.connections.createSynapse(activeSegment, previousActiveCells[1], .5)
tm.connections.createSynapse(activeSegment, previousActiveCells[2], .5)
# Weak inactive synapse.
tm.connections.createSynapse(activeSegment, previousActiveCells[3], .009)
tm.compute(previousActiveColumns, True)
tm.compute(activeColumns, True)
self.assertEqual(3, tm.connections.numSynapses(activeSegment))
def testReinforceCorrectlyActiveSegments(self):
tm = TemporalMemory(
columnDimensions=[32],
cellsPerColumn=4,
activationThreshold=3,
initialPermanence=.2,
connectedPermanence=.50,
minThreshold=2,
maxNewSynapseCount=4,
permanenceIncrement=.10,
permanenceDecrement=.08,
predictedSegmentDecrement=0.02,
seed=42)
prevActiveColumns = [0]
prevActiveCells = [0,1,2,3]
activeColumns = [1]
activeCell = 5
activeSegment = tm.connections.createSegment(activeCell)
as1 = tm.connections.createSynapse(activeSegment, prevActiveCells[0], .5)
as2 = tm.connections.createSynapse(activeSegment, prevActiveCells[1], .5)
as3 = tm.connections.createSynapse(activeSegment, prevActiveCells[2], .5)
is1 = tm.connections.createSynapse(activeSegment, 81, .5) #inactive synapse
tm.compute(prevActiveColumns, True)
tm.compute(activeColumns, True)
self.assertAlmostEqual(.6, tm.connections.dataForSynapse(as1).permanence)
self.assertAlmostEqual(.6, tm.connections.dataForSynapse(as2).permanence)
self.assertAlmostEqual(.6, tm.connections.dataForSynapse(as3).permanence)
self.assertAlmostEqual(.42, tm.connections.dataForSynapse(is1).permanence)
def testWriteRead(self):
tm1 = TemporalMemory(
columnDimensions=(32,),
cellsPerColumn=4,
activationThreshold=3,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=2,
maxNewSynapseCount=3,
permanenceIncrement=0.1,
permanenceDecrement=0.1,
predictedSegmentDecrement=0.0,
seed=42
)
self.serializationTestPrepare(tm1)
proto1 = TemporalMemoryProto_capnp.TemporalMemoryProto.new_message()
tm1.write(proto1)
# Write the proto to a temp file and read it back into a new proto
with tempfile.TemporaryFile() as f:
proto1.write(f)
f.seek(0)
proto2 = TemporalMemoryProto_capnp.TemporalMemoryProto.read(f)
# Load the deserialized proto
tm2 = TemporalMemory.read(proto2)
self.assertEqual(tm1, tm2)
self.serializationTestVerify(tm2)
def testLearnOnSegments(self):
tm = TemporalMemory(maxNewSynapseCount=2)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
connections.createSynapse(0, 37, 0.4)
connections.createSynapse(0, 477, 0.9)
connections.createSegment(1)
connections.createSynapse(1, 733, 0.7)
connections.createSegment(8)
connections.createSynapse(2, 486, 0.9)
connections.createSegment(100)
prevActiveSegments = set([0, 2])
learningSegments = set([1, 3])
prevActiveCells = set([23, 37, 733])
winnerCells = set([0])
prevWinnerCells = set([10, 11, 12, 13, 14])
predictedInactiveCells = set()
prevMatchingSegments = set()
tm.learnOnSegments(prevActiveSegments,
learningSegments,
prevActiveCells,
winnerCells,
prevWinnerCells,
connections,
predictedInactiveCells,
prevMatchingSegments)
# Check segment 0
synapseData = connections.dataForSynapse(0)
self.assertAlmostEqual(synapseData.permanence, 0.7)
synapseData = connections.dataForSynapse(1)
self.assertAlmostEqual(synapseData.permanence, 0.5)
synapseData = connections.dataForSynapse(2)
self.assertAlmostEqual(synapseData.permanence, 0.8)
# Check segment 1
synapseData = connections.dataForSynapse(3)
self.assertAlmostEqual(synapseData.permanence, 0.8)
self.assertEqual(len(connections.synapsesForSegment(1)), 2)
# Check segment 2
synapseData = connections.dataForSynapse(4)
self.assertAlmostEqual(synapseData.permanence, 0.9)
self.assertEqual(len(connections.synapsesForSegment(2)), 1)
# Check segment 3
self.assertEqual(len(connections.synapsesForSegment(3)), 2)
def testColumnForCell1D(self):
tm = TemporalMemory(
columnDimensions=[2048],
cellsPerColumn=5
)
self.assertEqual(tm.columnForCell(0), 0)
self.assertEqual(tm.columnForCell(4), 0)
self.assertEqual(tm.columnForCell(5), 1)
self.assertEqual(tm.columnForCell(10239), 2047)
def testMapCellsToColumns(self):
tm = TemporalMemory(
columnDimensions=[100],
cellsPerColumn=4
)
columnsForCells = tm.mapCellsToColumns(set([0, 1, 2, 5, 399]))
self.assertEqual(columnsForCells[0], set([0, 1, 2]))
self.assertEqual(columnsForCells[1], set([5]))
self.assertEqual(columnsForCells[99], set([399]))
def testColumnForCell2D(self):
tm = TemporalMemory(
columnDimensions=[64, 64],
cellsPerColumn=4
)
self.assertEqual(tm.columnForCell(0), 0)
self.assertEqual(tm.columnForCell(3), 0)
self.assertEqual(tm.columnForCell(4), 1)
self.assertEqual(tm.columnForCell(16383), 4095)
def testLearnOnSegments(self):
tm = TemporalMemory(maxNewSynapseCount=2)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
connections.createSynapse(0, 37, 0.4)
connections.createSynapse(0, 477, 0.9)
connections.createSegment(1)
connections.createSynapse(1, 733, 0.7)
connections.createSegment(8)
connections.createSynapse(2, 486, 0.9)
connections.createSegment(100)
prevActiveSegments = set([0, 2])
learningSegments = set([1, 3])
prevActiveCells = set([23, 37, 733])
winnerCells = set([0])
prevWinnerCells = set([10, 11, 12, 13, 14])
predictedInactiveCells = set()
prevMatchingSegments = set()
tm.learnOnSegments(prevActiveSegments,
learningSegments,
prevActiveCells,
winnerCells,
prevWinnerCells,
connections,
predictedInactiveCells,
prevMatchingSegments)
# Check segment 0
synapseData = connections.dataForSynapse(0)
self.assertAlmostEqual(synapseData.permanence, 0.7)
synapseData = connections.dataForSynapse(1)
self.assertAlmostEqual(synapseData.permanence, 0.5)
synapseData = connections.dataForSynapse(2)
self.assertAlmostEqual(synapseData.permanence, 0.8)
# Check segment 1
synapseData = connections.dataForSynapse(3)
self.assertAlmostEqual(synapseData.permanence, 0.8)
self.assertEqual(len(connections.synapsesForSegment(1)), 2)
# Check segment 2
synapseData = connections.dataForSynapse(4)
self.assertAlmostEqual(synapseData.permanence, 0.9)
self.assertEqual(len(connections.synapsesForSegment(2)), 1)
# Check segment 3
self.assertEqual(len(connections.synapsesForSegment(3)), 2)
def testLeastUsedCell(self):
tm = TemporalMemory(columnDimensions=[2], cellsPerColumn=2, seed=42)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 3, 0.3)
for _ in range(100):
# Never pick cell 0, always pick cell 1
self.assertEqual(tm.leastUsedCell(tm.cellsForColumn(0)), 1)
def testLearnOnSegments(self):
tm = TemporalMemory(maxNewSynapseCount=2)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
connections.createSynapse(0, 37, 0.4)
connections.createSynapse(0, 477, 0.9)
connections.createSegment(1)
connections.createSynapse(1, 733, 0.7)
connections.createSegment(8)
connections.createSynapse(2, 486, 0.9)
connections.createSegment(100)
prevActiveSegments = set([0, 2])
learningSegments = set([1, 3])
prevActiveSynapsesForSegment = {0: set([0, 1]),
1: set([3])}
winnerCells = set([0])
prevWinnerCells = set([10, 11, 12, 13, 14])
tm.learnOnSegments(prevActiveSegments,
learningSegments,
prevActiveSynapsesForSegment,
winnerCells,
prevWinnerCells,
connections)
# Check segment 0
(_, _, permanence) = connections.dataForSynapse(0)
self.assertAlmostEqual(permanence, 0.7)
(_, _, permanence) = connections.dataForSynapse(1)
self.assertAlmostEqual(permanence, 0.5)
(_, _, permanence) = connections.dataForSynapse(2)
self.assertAlmostEqual(permanence, 0.8)
# Check segment 1
(_, _, permanence) = connections.dataForSynapse(3)
self.assertAlmostEqual(permanence, 0.8)
self.assertEqual(len(connections.synapsesForSegment(1)), 2)
# Check segment 2
(_, _, permanence) = connections.dataForSynapse(4)
self.assertAlmostEqual(permanence, 0.9)
self.assertEqual(len(connections.synapsesForSegment(2)), 1)
# Check segment 3
self.assertEqual(len(connections.synapsesForSegment(3)), 2)
def testPickCellsToLearnOnAvoidDuplicates(self):
tm = TemporalMemory(seed=42)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
winnerCells = set([23])
# Ensure that no additional (duplicate) cells were picked
self.assertEqual(tm.pickCellsToLearnOn(2, 0, winnerCells), set())
def testPickCellsToLearnOnAvoidDuplicates(self):
tm = TemporalMemory(seed=42)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
winnerCells = set([23])
# Ensure that no additional (duplicate) cells were picked
self.assertEqual(tm.pickCellsToLearnOn(2, 0, winnerCells),
set())
def testAdaptSegmentToMin(self):
tm = TemporalMemory()
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.1)
connections.createSynapse(0, 1, 0.3)
tm.adaptSegment(connections, [], tm.permanenceIncrement,
tm.permanenceDecrement, 0)
synapses = connections.synapsesForSegment(0)
self.assertFalse(0 in synapses)
def testCellsForColumnInvalidColumn(self):
tm = TemporalMemory(columnDimensions=[64, 64], cellsPerColumn=4)
try:
tm.cellsForColumn(4095)
except IndexError:
self.fail("IndexError raised unexpectedly")
args = [4096]
self.assertRaises(IndexError, tm.cellsForColumn, *args)
args = [-1]
self.assertRaises(IndexError, tm.cellsForColumn, *args)
def testColumnForCellInvalidCell(self):
tm = TemporalMemory(columnDimensions=[64, 64], cellsPerColumn=4)
try:
tm.columnForCell(16383)
except IndexError:
self.fail("IndexError raised unexpectedly")
args = [16384]
self.assertRaises(IndexError, tm.columnForCell, *args)
args = [-1]
self.assertRaises(IndexError, tm.columnForCell, *args)
def testWrite(self):
tm1 = TemporalMemory(
columnDimensions=[100],
cellsPerColumn=4,
activationThreshold=7,
initialPermanence=0.37,
connectedPermanence=0.58,
minThreshold=4,
maxNewSynapseCount=18,
permanenceIncrement=0.23,
permanenceDecrement=0.08,
seed=91
)
# Run some data through before serializing
self.patternMachine = PatternMachine(100, 4)
self.sequenceMachine = SequenceMachine(self.patternMachine)
sequence = self.sequenceMachine.generateFromNumbers(range(5))
for _ in range(3):
for pattern in sequence:
tm1.compute(pattern)
proto1 = TemporalMemoryProto_capnp.TemporalMemoryProto.new_message()
tm1.write(proto1)
# Write the proto to a temp file and read it back into a new proto
with tempfile.TemporaryFile() as f:
proto1.write(f)
f.seek(0)
proto2 = TemporalMemoryProto_capnp.TemporalMemoryProto.read(f)
# Load the deserialized proto
tm2 = TemporalMemory.read(proto2)
# Check that the two temporal memory objects have the same attributes
self.assertEqual(tm1, tm2)
# Run a couple records through after deserializing and check results match
tm1.compute(self.patternMachine.get(0))
tm2.compute(self.patternMachine.get(0))
self.assertEqual(tm1.activeCells, tm2.activeCells)
self.assertEqual(tm1.predictiveCells, tm2.predictiveCells)
self.assertEqual(tm1.winnerCells, tm2.winnerCells)
self.assertEqual(tm1.connections, tm2.connections)
tm1.compute(self.patternMachine.get(3))
tm2.compute(self.patternMachine.get(3))
self.assertEqual(tm1.activeCells, tm2.activeCells)
self.assertEqual(tm1.predictiveCells, tm2.predictiveCells)
self.assertEqual(tm1.winnerCells, tm2.winnerCells)
self.assertEqual(tm1.connections, tm2.connections)
def testActivateCorrectlyPredictiveCells(self):
tm = TemporalMemory(columnDimensions=[32],
cellsPerColumn=4,
activationThreshold=3,
initialPermanence=.21,
connectedPermanence=.5,
minThreshold=2,
maxNewSynapseCount=3,
permanenceIncrement=.10,
permanenceDecrement=.10,
predictedSegmentDecrement=0.0,
seed=42)
previousActiveColumns = [0]
activeColumns = [1]
previousActiveCells = [0, 1, 2, 3]
expectedActiveCells = [4]
activeSegment = tm.connections.createSegment(expectedActiveCells[0])
tm.connections.createSynapse(activeSegment, previousActiveCells[0], .5)
tm.connections.createSynapse(activeSegment, previousActiveCells[1], .5)
tm.connections.createSynapse(activeSegment, previousActiveCells[2], .5)
tm.connections.createSynapse(activeSegment, previousActiveCells[3], .5)
tm.compute(previousActiveColumns, True)
self.assertEqual(expectedActiveCells, tm.getPredictiveCells())
tm.compute(activeColumns, True)
self.assertEqual(expectedActiveCells, tm.getActiveCells())
def testLeastUsedCell(self):
tm = TemporalMemory(
columnDimensions=[2],
cellsPerColumn=2,
seed=42
)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 3, 0.3)
for _ in range(100):
# Never pick cell 0, always pick cell 1
self.assertEqual(tm.leastUsedCell(tm.cellsForColumn(0)), 1)
def testAdaptSegmentToMin(self):
tm = TemporalMemory()
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.1)
connections.createSynapse(0, 1, 0.3)
tm.adaptSegment(connections, [],
tm.permanenceIncrement,
tm.permanenceDecrement, 0)
synapses = connections.synapsesForSegment(0)
self.assertFalse(0 in synapses)
def testBestMatchingCell(self):
tm = TemporalMemory(connectedPermanence=0.50, minThreshold=1, seed=42)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
connections.createSynapse(0, 37, 0.4)
connections.createSynapse(0, 477, 0.9)
connections.createSegment(0)
connections.createSynapse(1, 49, 0.9)
connections.createSynapse(1, 3, 0.8)
connections.createSegment(1)
connections.createSynapse(2, 733, 0.7)
connections.createSegment(108)
connections.createSynapse(3, 486, 0.9)
activeCells = set([23, 37, 49, 733])
self.assertEqual(
tm.bestMatchingCell(tm.cellsForColumn(0), activeCells), (0, 0))
self.assertEqual(
tm.bestMatchingCell(
tm.cellsForColumn(3), # column containing cell 108
activeCells),
(103, None)) # Random cell from column
self.assertEqual(
tm.bestMatchingCell(tm.cellsForColumn(999), activeCells),
(31979, None)) # Random cell from column
def testNewSegmentAddSynapsesToSubsetOfWinnerCells(self):
tm = TemporalMemory(columnDimensions=[32],
cellsPerColumn=4,
activationThreshold=3,
initialPermanence=.21,
connectedPermanence=.50,
minThreshold=2,
maxNewSynapseCount=2,
permanenceIncrement=.10,
permanenceDecrement=.10,
predictedSegmentDecrement=0.0,
seed=42)
previousActiveColumns = [0, 1, 2]
activeColumns = [4]
tm.compute(previousActiveColumns, True)
prevWinnerCells = tm.getWinnerCells() #[0, 8, 7]
self.assertEqual(3, len(prevWinnerCells))
tm.compute(activeColumns, True)
winnerCells = tm.getWinnerCells() #[18]
self.assertEqual(1, len(winnerCells))
segments = tm.connections.segmentsForCell(winnerCells[0])
self.assertEqual(1, len(segments))
synapses = tm.connections.synapsesForSegment(segments[0])
self.assertEqual(2, len(synapses))
for synapse in synapses:
synapseData = tm.connections.dataForSynapse(synapse)
self.assertAlmostEqual(.21, synapseData.permanence)
self.assertTrue(synapseData.presynapticCell in prevWinnerCells)
def testPickCellsToLearnOn(self):
tm = TemporalMemory(seed=42)
connections = tm.connections
connections.createSegment(0)
winnerCells = set([4, 47, 58, 93])
self.assertEqual(tm.pickCellsToLearnOn(2, 0, winnerCells),
set([4, 93])) # randomly picked
self.assertEqual(tm.pickCellsToLearnOn(100, 0, winnerCells),
set([4, 47, 58, 93]))
self.assertEqual(tm.pickCellsToLearnOn(0, 0, winnerCells), set())
def initModules(self, categories, inputIdx):
modulesNames = {'generalSP', 'generalTM'}
nWords = len(categories[inputIdx['wordInput']])
nActions = len(categories[inputIdx['actionInput']])
inputDimensions = max(
self.wordEncoder.getWidth(),
self.actionEncoder.getWidth()
)
columnDimensions = (max((nWords + nActions),
len(self.trainingData)) * 2, )
defaultGeneralSPParams = {
'inputDimensions': inputDimensions,
'columnDimensions': columnDimensions,
'seed': self.spSeed
}
defaultGeneralTMParams = {
'columnDimensions': columnDimensions,
'seed': self.tmSeed
}
if (self.modulesParams is not None) and\
(set(self.modulesParams) == modulesNames):
self.modulesParams['generalSP'].update(defaultGeneralSPParams)
self.modulesParams['generalTM'].update(defaultGeneralTMParams)
self.generalSP = SpatialPooler(**self.modulesParams['generalSP'])
self.generalTM = TemporalMemory(**self.modulesParams['generalTM'])
print("Using external Parameters!")
else:
self.generalSP = SpatialPooler(**defaultGeneralSPParams)
self.generalTM = TemporalMemory(**defaultGeneralTMParams)
print("External parameters invalid or not found, using"\
" the default ones")
self.classifier = CLAClassifierCond(
steps=[1, 2],
alpha=0.1,
actValueAlpha=0.3,
verbosity=0
)
def testCellsForColumnInvalidColumn(self):
tm = TemporalMemory(
columnDimensions=[64, 64],
cellsPerColumn=4
)
try:
tm.cellsForColumn(4095)
except IndexError:
self.fail("IndexError raised unexpectedly")
args = [4096]
self.assertRaises(IndexError, tm.cellsForColumn, *args)
args = [-1]
self.assertRaises(IndexError, tm.cellsForColumn, *args)
def testColumnForCellInvalidCell(self):
tm = TemporalMemory(
columnDimensions=[64, 64],
cellsPerColumn=4
)
try:
tm.columnForCell(16383)
except IndexError:
self.fail("IndexError raised unexpectedly")
args = [16384]
self.assertRaises(IndexError, tm.columnForCell, *args)
args = [-1]
self.assertRaises(IndexError, tm.columnForCell, *args)
def testPickCellsToLearnOn(self):
tm = TemporalMemory(seed=42)
connections = tm.connections
connections.createSegment(0)
winnerCells = set([4, 47, 58, 93])
self.assertEqual(tm.pickCellsToLearnOn(2, 0, winnerCells),
set([4, 58])) # randomly picked
self.assertEqual(tm.pickCellsToLearnOn(100, 0, winnerCells),
set([4, 47, 58, 93]))
self.assertEqual(tm.pickCellsToLearnOn(0, 0, winnerCells),
set())
def learnOnApicalSegments(self, prevActiveSegments, learningSegments,
prevActiveCells, winnerCells, connections,
predictedInactiveCells, prevMatchingSegments):
"""
Phase 3: Perform learning by adapting segments.
Pseudocode:
- (learning) for each prev active or learning segment
- if learning segment or from winner cell
- strengthen active synapses
- weaken inactive synapses
- if learning segment
- add some synapses to the segment
- subsample from prev winner cells
@param prevActiveSegments (set) Indices of active segments in `t-1`
@param learningSegments (set) Indices of learning segments in `t`
@param prevActiveCells (set) Indices of active cells in `t-1`
@param winnerCells (set) Indices of winner cells in `t`
@param connections (Connections) Connectivity of layer
@param predictedInactiveCells (set) Indices of predicted inactive cells
@param prevMatchingSegments (set) Indices of segments with
"""
for winnerCell in winnerCells:
winnerSegments = connections.segmentsForCell(winnerCell)
if len(winnerSegments
& (prevActiveSegments | learningSegments)) == 0:
maxActiveSynapses = 0
winnerSegment = None
for segment in winnerSegments:
activeSynapses = TemporalMemory.activeSynapsesForSegment(
segment, prevActiveCells, connections)
numActiveSynapses = len(activeSynapses)
if numActiveSynapses > maxActiveSynapses:
maxActiveSynapses = numActiveSynapses
winnerSegment = segment
if winnerSegment is not None:
learningSegments.add(winnerSegment)
for segment in prevActiveSegments | learningSegments:
isLearningSegment = segment in learningSegments
isFromWinnerCell = connections.cellForSegment(
segment) in winnerCells
activeSynapses = self.activeSynapsesForSegment(
segment, prevActiveCells, connections)
if isLearningSegment or isFromWinnerCell:
self.adaptSegment(segment, activeSynapses, connections,
self.permanenceIncrement,
self.permanenceDecrement)
if isLearningSegment:
n = self.maxNewSynapseCount - len(activeSynapses)
for presynapticCell in self.pickCellsToLearnOn(
n, segment, prevActiveCells, connections):
connections.createSynapse(segment, presynapticCell,
self.initialPermanence)
def testGetBestMatchingSegment(self):
tm = TemporalMemory(
connectedPermanence=0.50,
minThreshold=1
)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
connections.createSynapse(0, 37, 0.4)
connections.createSynapse(0, 477, 0.9)
connections.createSegment(0)
connections.createSynapse(1, 49, 0.9)
connections.createSynapse(1, 3, 0.8)
connections.createSegment(1)
connections.createSynapse(2, 733, 0.7)
connections.createSegment(8)
connections.createSynapse(3, 486, 0.9)
activeSynapsesForSegment = {
0: set([0, 1]),
1: set([3]),
2: set([5])
}
self.assertEqual(tm.getBestMatchingSegment(0,
activeSynapsesForSegment,
connections),
(0, set([0, 1])))
self.assertEqual(tm.getBestMatchingSegment(1,
activeSynapsesForSegment,
connections),
(2, set([5])))
self.assertEqual(tm.getBestMatchingSegment(8,
activeSynapsesForSegment,
connections),
(None, None))
self.assertEqual(tm.getBestMatchingSegment(100,
activeSynapsesForSegment,
connections),
(None, None))
def testPunishMatchingSegmentsInInactiveColumns(self):
tm = TemporalMemory(
columnDimensions=[32],
cellsPerColumn=4,
activationThreshold=3,
initialPermanence=.2,
connectedPermanence=.50,
minThreshold=2,
maxNewSynapseCount=4,
permanenceIncrement=.10,
permanenceDecrement=.10,
predictedSegmentDecrement=0.02,
seed=42)
previousActiveColumns = [0]
previousActiveCells = [0, 1, 2, 3]
activeColumns = [1]
previousInactiveCell = 81
activeSegment = tm.connections.createSegment(42)
as1 = tm.connections.createSynapse(activeSegment,
previousActiveCells[0], .5)
as2 = tm.connections.createSynapse(activeSegment,
previousActiveCells[1], .5)
as3 = tm.connections.createSynapse(activeSegment,
previousActiveCells[2], .5)
is1 = tm.connections.createSynapse(activeSegment,
previousInactiveCell, .5)
matchingSegment = tm.connections.createSegment(43)
as4 = tm.connections.createSynapse(matchingSegment,
previousActiveCells[0], .5)
as5 = tm.connections.createSynapse(matchingSegment,
previousActiveCells[1], .5)
is2 = tm.connections.createSynapse(matchingSegment,
previousInactiveCell, .5)
tm.compute(previousActiveColumns, True)
tm.compute(activeColumns, True)
self.assertAlmostEqual(.48, tm.connections.dataForSynapse(as1).permanence)
self.assertAlmostEqual(.48, tm.connections.dataForSynapse(as2).permanence)
self.assertAlmostEqual(.48, tm.connections.dataForSynapse(as3).permanence)
self.assertAlmostEqual(.48, tm.connections.dataForSynapse(as4).permanence)
self.assertAlmostEqual(.48, tm.connections.dataForSynapse(as5).permanence)
self.assertAlmostEqual(.50, tm.connections.dataForSynapse(is1).permanence)
self.assertAlmostEqual(.50, tm.connections.dataForSynapse(is2).permanence)
def initTM(self, overrides=None):
params = self.defaultTMParams
params.update(overrides or {})
self.tm = TemporalMemory(**params)
print "Initialized new TM with parameters:"
print pprint.pformat(params)
print
def testReadTestFile(self):
with open("TemporalMemorySerializationWrite.tmp", "r") as f:
proto = TemporalMemoryProto_capnp.TemporalMemoryProto.read(f)
# Load the deserialized proto
tm = TemporalMemory.read(proto)
self.serializationTestVerify(tm)
def testReadTestFile(self):
with open("TemporalMemorySerializationWrite.tmp", "r") as f:
proto = TemporalMemoryProto_capnp.TemporalMemoryProto.read(f)
# Load the deserialized proto
tm = TemporalMemory.read(proto)
self.serializationTestVerify(tm)
def testBurstColumns(self):
tm = TemporalMemory(
cellsPerColumn=4,
connectedPermanence=0.50,
minThreshold=1,
seed=42
)
connections = tm.connections
connections.createSegment(0)
connections.createSynapse(0, 23, 0.6)
connections.createSynapse(0, 37, 0.4)
connections.createSynapse(0, 477, 0.9)
connections.createSegment(0)
connections.createSynapse(1, 49, 0.9)
connections.createSynapse(1, 3, 0.8)
connections.createSegment(1)
connections.createSynapse(2, 733, 0.7)
connections.createSegment(108)
connections.createSynapse(3, 486, 0.9)
activeColumns = set([0, 1, 26])
predictedColumns = set([26])
prevActiveSynapsesForSegment = {
0: set([0, 1]),
1: set([3]),
2: set([5])
}
(activeCells,
winnerCells,
learningSegments) = tm.burstColumns(activeColumns,
predictedColumns,
prevActiveSynapsesForSegment,
connections)
self.assertEqual(activeCells, set([0, 1, 2, 3, 4, 5, 6, 7]))
self.assertEqual(winnerCells, set([0, 6])) # 6 is randomly chosen cell
self.assertEqual(learningSegments, set([0, 4])) # 4 is new segment created
# Check that new segment was added to winner cell (6) in column 1
self.assertEqual(connections.segmentsForCell(6), set([4]))
def testMatchingSegmentAddSynapsesToAllWinnerCells(self):
tm = TemporalMemory(columnDimensions=[32],
cellsPerColumn=1,
activationThreshold=3,
initialPermanence=.21,
connectedPermanence=.50,
minThreshold=1,
maxNewSynapseCount=3,
permanenceIncrement=.10,
permanenceDecrement=.10,
predictedSegmentDecrement=0.0,
seed=42)
previousActiveColumns = [0, 1]
prevWinnerCells = [0, 1]
activeColumns = [4]
matchingSegment = tm.connections.createSegment(4)
tm.connections.createSynapse(matchingSegment, 0, .5)
tm.compute(previousActiveColumns, True)
self.assertEqual(prevWinnerCells, tm.getWinnerCells())
tm.compute(activeColumns)
synapses = tm.connections.synapsesForSegment(matchingSegment)
self.assertEqual(2, len(synapses))
synapseData = tm.connections.dataForSynapse(synapses[1])
self.assertAlmostEqual(.21, synapseData.permanence)
self.assertEqual(prevWinnerCells[1], synapseData.presynapticCell)
def testActivateCorrectlyPredictiveCells(self):
tm = TemporalMemory(
columnDimensions=[32],
cellsPerColumn=4,
activationThreshold=3,
initialPermanence=.21,
connectedPermanence=.5,
minThreshold=2,
maxNewSynapseCount=3,
permanenceIncrement=.10,
permanenceDecrement=.10,
predictedSegmentDecrement=0.0,
seed=42)
previousActiveColumns = [0]
activeColumns = [1]
previousActiveCells = [0,1,2,3]
expectedActiveCells = [4]
activeSegment = tm.connections.createSegment(expectedActiveCells[0])
tm.connections.createSynapse(activeSegment, previousActiveCells[0], .5)
tm.connections.createSynapse(activeSegment, previousActiveCells[1], .5)
tm.connections.createSynapse(activeSegment, previousActiveCells[2], .5)
tm.connections.createSynapse(activeSegment, previousActiveCells[3], .5)
tm.compute(previousActiveColumns, True)
self.assertEqual(expectedActiveCells, tm.getPredictiveCells())
tm.compute(activeColumns, True)
self.assertEqual(expectedActiveCells, tm.getActiveCells())
def testRecycleWeakestSynapseToMakeRoomForNewSynapse(self):
tm = TemporalMemory(columnDimensions=[32],
cellsPerColumn=1,
activationThreshold=3,
initialPermanence=.21,
connectedPermanence=.50,
minThreshold=1,
maxNewSynapseCount=3,
permanenceIncrement=.02,
permanenceDecrement=.02,
predictedSegmentDecrement=0.0,
seed=42,
maxSynapsesPerSegment=3)
prevActiveColumns = [0, 1, 2]
prevWinnerCells = [0, 1, 2]
activeColumns = [4]
matchingSegment = tm.connections.createSegment(4)
tm.connections.createSynapse(matchingSegment, 81, .6)
weakestSynapse = tm.connections.createSynapse(matchingSegment, 0, .11)
tm.compute(prevActiveColumns)
self.assertEqual(prevWinnerCells, tm.getWinnerCells())
tm.compute(activeColumns)
synapseData = tm.connections.dataForSynapse(weakestSynapse)
self.assertNotEqual(0, synapseData.presynapticCell)
self.assertFalse(synapseData.destroyed)
self.assertAlmostEqual(.21, synapseData.permanence)
