def testDestroySegment(self):
""" Creates a segment, destroys it, and makes sure it got destroyed along
with all of its synapses.
"""
connections = Connections(1024)
connections.createSegment(10)
segment2 = connections.createSegment(20)
connections.createSegment(30)
connections.createSegment(40)
connections.createSynapse(segment2, 80, 0.85)
connections.createSynapse(segment2, 81, 0.85)
connections.createSynapse(segment2, 82, 0.15)
self.assertEqual(4, connections.numSegments())
self.assertEqual(3, connections.numSynapses())
connections.destroySegment(segment2)
self.assertEqual(3, connections.numSegments())
self.assertEqual(0, connections.numSynapses())
args = [segment2]
self.assertRaises(ValueError, connections.synapsesForSegment, *args)
active, matching = connections.computeActivity([80, 81, 82], .5, 2, .1, 1)
self.assertEqual(len(active), 0)
self.assertEqual(len(matching), 0)
def testDestroySegment(self):
""" Creates a segment, destroys it, and makes sure it got destroyed along
with all of its synapses.
"""
connections = Connections(1024)
connections.createSegment(10)
segment2 = connections.createSegment(20)
connections.createSegment(30)
connections.createSegment(40)
connections.createSynapse(segment2, 80, 0.85)
connections.createSynapse(segment2, 81, 0.85)
connections.createSynapse(segment2, 82, 0.15)
self.assertEqual(4, connections.numSegments())
self.assertEqual(3, connections.numSynapses())
connections.destroySegment(segment2)
self.assertEqual(3, connections.numSegments())
self.assertEqual(0, connections.numSynapses())
args = [segment2]
self.assertRaises(ValueError, connections.synapsesForSegment, *args)
active, matching = connections.computeActivity([80, 81, 82], .5, 2, .1,
1)
self.assertEqual(len(active), 0)
self.assertEqual(len(matching), 0)
def testWriteRead(self):
c1 = Connections(1024)
# Add data before serializing
s1 = c1.createSegment(0)
c1.createSynapse(s1, 254, 0.1173)
s2 = c1.createSegment(100)
c1.createSynapse(s2, 20, 0.3)
c1.createSynapse(s1, 40, 0.3)
s3 = c1.createSegment(0)
c1.createSynapse(s3, 0, 0.5)
c1.createSynapse(s3, 1, 0.5)
s4 = c1.createSegment(10)
c1.createSynapse(s4, 0, 0.5)
c1.createSynapse(s4, 1, 0.5)
c1.destroySegment(s4)
proto1 = ConnectionsProto_capnp.ConnectionsProto.new_message()
c1.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 = ConnectionsProto_capnp.ConnectionsProto.read(f)
# Load the deserialized proto
c2 = Connections.read(proto2)
# Check that the two connections objects are functionally equal
self.assertEqual(c1, c2)
def testComputeActivity(self):
""" Creates a sample set of connections, and makes sure that computing the
activity for a collection of cells with no activity returns the right
activity data.
"""
connections = Connections(1024)
# Cell with 1 segment.
# Segment with:
# - 1 connected synapse: active
# - 2 matching synapses
segment1a = connections.createSegment(10)
connections.createSynapse(segment1a, 150, .85)
connections.createSynapse(segment1a, 151, .15)
# Cell with 1 segment.
# Segment with:
# - 2 connected synapse: 2 active
# - 3 matching synapses: 3 active
segment2a = connections.createSegment(20)
connections.createSynapse(segment2a, 80, .85)
connections.createSynapse(segment2a, 81, .85)
synapse = connections.createSynapse(segment2a, 82, .85)
connections.updateSynapsePermanence(synapse, .15)
inputVec = [50, 52, 53, 80, 81, 82, 150, 151]
(numActiveConnected,
numActivePotential) = connections.computeActivity(inputVec, .5)
self.assertEqual(1, numActiveConnected[segment1a.flatIdx])
self.assertEqual(2, numActivePotential[segment1a.flatIdx])
self.assertEqual(2, numActiveConnected[segment2a.flatIdx])
self.assertEqual(3, numActivePotential[segment2a.flatIdx])
def testDestroySegment(self):
""" Creates a segment, destroys it, and makes sure it got destroyed along
with all of its synapses.
"""
connections = Connections(1024)
connections.createSegment(10)
segment2 = connections.createSegment(20)
connections.createSegment(30)
connections.createSegment(40)
connections.createSynapse(segment2, 80, 0.85)
connections.createSynapse(segment2, 81, 0.85)
connections.createSynapse(segment2, 82, 0.15)
self.assertEqual(4, connections.numSegments())
self.assertEqual(3, connections.numSynapses())
connections.destroySegment(segment2)
self.assertEqual(3, connections.numSegments())
self.assertEqual(0, connections.numSynapses())
(numActiveConnected,
numActivePotential) = connections.computeActivity([80, 81, 82], 0.5)
self.assertEqual(0, numActiveConnected[segment2.flatIdx])
self.assertEqual(0, numActivePotential[segment2.flatIdx])
def testDestroySegment(self):
""" Creates a segment, destroys it, and makes sure it got destroyed along
with all of its synapses.
"""
connections = Connections(1024)
connections.createSegment(10)
segment2 = connections.createSegment(20)
connections.createSegment(30)
connections.createSegment(40)
connections.createSynapse(segment2, 80, 0.85)
connections.createSynapse(segment2, 81, 0.85)
connections.createSynapse(segment2, 82, 0.15)
self.assertEqual(4, connections.numSegments())
self.assertEqual(3, connections.numSynapses())
connections.destroySegment(segment2)
self.assertEqual(3, connections.numSegments())
self.assertEqual(0, connections.numSynapses())
(numActiveConnected,
numActivePotential) = connections.computeActivity([80, 81, 82], 0.5)
self.assertEqual(0, numActiveConnected[segment2.flatIdx])
self.assertEqual(0, numActivePotential[segment2.flatIdx])
def testWriteRead(self):
c1 = Connections(1024)
# Add data before serializing
s1 = c1.createSegment(0)
c1.createSynapse(s1, 254, 0.1173)
s2 = c1.createSegment(100)
c1.createSynapse(s2, 20, 0.3)
c1.createSynapse(s1, 40, 0.3)
s3 = c1.createSegment(0)
c1.createSynapse(s3, 0, 0.5)
c1.createSynapse(s3, 1, 0.5)
s4 = c1.createSegment(10)
c1.createSynapse(s4, 0, 0.5)
c1.createSynapse(s4, 1, 0.5)
c1.destroySegment(s4)
proto1 = ConnectionsProto_capnp.ConnectionsProto.new_message()
c1.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 = ConnectionsProto_capnp.ConnectionsProto.read(f)
# Load the deserialized proto
c2 = Connections.read(proto2)
# Check that the two connections objects are functionally equal
self.assertEqual(c1, c2)
def testComputeActivity(self):
""" Creates a sample set of connections, and makes sure that computing the
activity for a collection of cells with no activity returns the right
activity data.
"""
connections = Connections(1024)
# Cell with 1 segment.
# Segment with:
# - 1 connected synapse: active
# - 2 matching synapses
segment1a = connections.createSegment(10)
connections.createSynapse(segment1a, 150, .85)
connections.createSynapse(segment1a, 151, .15)
# Cell with 1 segment.
# Segment with:
# - 2 connected synapse: 2 active
# - 3 matching synapses: 3 active
segment2a = connections.createSegment(20)
connections.createSynapse(segment2a, 80, .85)
connections.createSynapse(segment2a, 81, .85)
synapse = connections.createSynapse(segment2a, 82, .85)
connections.updateSynapsePermanence(synapse, .15)
inputVec = [50, 52, 53, 80, 81, 82, 150, 151]
(numActiveConnected,
numActivePotential) = connections.computeActivity(inputVec, .5)
self.assertEqual(1, numActiveConnected[segment1a.flatIdx])
self.assertEqual(2, numActivePotential[segment1a.flatIdx])
self.assertEqual(2, numActiveConnected[segment2a.flatIdx])
self.assertEqual(3, numActivePotential[segment2a.flatIdx])
def testComputeActivity(self):
""" Creates a sample set of connections, and makes sure that computing the
activity for a collection of cells with no activity returns the right
activity data.
"""
connections = Connections(1024)
# Cell with 1 segment.
# Segment with:
# - 1 connected synapse: active
# - 2 matching synapses
segment1a = connections.createSegment(10)
connections.createSynapse(segment1a, 150, .85)
connections.createSynapse(segment1a, 151, .15)
# Cell with 2 segment.
# Segment with:
# - 2 connected synapse: 2 active
# - 3 matching synapses: 3 active
segment2a = connections.createSegment(20)
connections.createSynapse(segment2a, 80, .85)
connections.createSynapse(segment2a, 81, .85)
synapse = connections.createSynapse(segment2a, 82, .85)
connections.updateSynapsePermanence(synapse, .15)
# Segment with:
# - 2 connected synapses: 1 active, 1 inactive
# - 3 matching synapses: 2 active, 1 inactive
# - 1 non-matching synapse: 1 active
segment2b = connections.createSegment(20)
connections.createSynapse(segment2b, 50, .85)
connections.createSynapse(segment2b, 51, .85)
connections.createSynapse(segment2b, 52, .15)
connections.createSynapse(segment2b, 53, .05)
# Cell with one segment.
# Segment with:
# - 1 non-matching synapse: 1 active
segment3a = connections.createSegment(30)
connections.createSynapse(segment3a, 53, .05)
inputVec = [50, 52, 53, 80, 81, 82, 150, 151]
active, matching = connections.computeActivity(inputVec, .5, 2, .1, 1)
self.assertEqual(1, len(active))
self.assertEqual(segment2a, active[0].segment)
self.assertEqual(2, active[0].overlap)
self.assertEqual(3, len(matching))
self.assertEqual(segment1a, matching[0].segment)
self.assertEqual(2, matching[0].overlap)
self.assertEqual(segment2a, matching[1].segment)
self.assertEqual(3, matching[1].overlap)
self.assertEqual(segment2b, matching[2].segment)
self.assertEqual(2, matching[2].overlap)
def testComputeActivity(self):
""" Creates a sample set of connections, and makes sure that computing the
activity for a collection of cells with no activity returns the right
activity data.
"""
connections = Connections(1024)
# Cell with 1 segment.
# Segment with:
# - 1 connected synapse: active
# - 2 matching synapses
segment1a = connections.createSegment(10)
connections.createSynapse(segment1a, 150, .85)
connections.createSynapse(segment1a, 151, .15)
# Cell with 2 segment.
# Segment with:
# - 2 connected synapse: 2 active
# - 3 matching synapses: 3 active
segment2a = connections.createSegment(20)
connections.createSynapse(segment2a, 80, .85)
connections.createSynapse(segment2a, 81, .85)
synapse = connections.createSynapse(segment2a, 82, .85)
connections.updateSynapsePermanence(synapse, .15)
# Segment with:
# - 2 connected synapses: 1 active, 1 inactive
# - 3 matching synapses: 2 active, 1 inactive
# - 1 non-matching synapse: 1 active
segment2b = connections.createSegment(20)
connections.createSynapse(segment2b, 50, .85)
connections.createSynapse(segment2b, 51, .85)
connections.createSynapse(segment2b, 52, .15)
connections.createSynapse(segment2b, 53, .05)
# Cell with one segment.
# Segment with:
# - 1 non-matching synapse: 1 active
segment3a = connections.createSegment(30)
connections.createSynapse(segment3a, 53, .05)
inputVec = [50, 52, 53, 80, 81, 82, 150, 151]
active, matching = connections.computeActivity(inputVec, .5, 2, .1, 1)
self.assertEqual(1, len(active))
self.assertEqual(segment2a, active[0].segment)
self.assertEqual(2, active[0].overlap)
self.assertEqual(3, len(matching))
self.assertEqual(segment1a, matching[0].segment)
self.assertEqual(2, matching[0].overlap)
self.assertEqual(segment2a, matching[1].segment)
self.assertEqual(3, matching[1].overlap)
self.assertEqual(segment2b, matching[2].segment)
self.assertEqual(2, matching[2].overlap)
def testCreateSegment(self):
connections = Connections(1024)
segment1 = connections.createSegment(10)
self.assertEqual(segment1.cell, 10)
segment2 = connections.createSegment(10)
self.assertEqual(segment2.cell, 10)
self.assertEqual([segment1, segment2],
list(connections.segmentsForCell(10)))
def testCreateSegment(self):
connections = Connections(1024)
segment1 = connections.createSegment(10)
self.assertEqual(segment1.cell, 10)
segment2 = connections.createSegment(10)
self.assertEqual(segment2.cell, 10)
self.assertEqual([segment1, segment2],
list(connections.segmentsForCell(10)))
def testCreateSegmentReuse(self):
connections = Connections(1024, 2)
segment1 = connections.createSegment(42)
connections.createSynapse(segment1, 1, .5)
connections.createSynapse(segment1, 2, .5)
# Let some time pass.
connections.startNewIteration()
connections.startNewIteration()
connections.startNewIteration()
# Create a segment with 3 synapse.
segment2 = connections.createSegment(42)
connections.createSynapse(segment2, 1, .5)
connections.createSynapse(segment2, 2, .5)
connections.createSynapse(segment2, 3, .5)
connections.startNewIteration()
# Give the first segment some activity.
connections.recordSegmentActivity(segment1)
# Create a new segment with 1 synapse.
segment3 = connections.createSegment(42)
connections.createSynapse(segment3, 1, .5)
segments = connections.segmentsForCell(42)
self.assertEqual(2, len(segments))
# Verify first segment is still there with the same synapses.
self.assertEqual(
set([1, 2]),
set(synapse.presynapticCell
for synapse in connections.synapsesForSegment(segments[0])))
# Verify second segment has been replaced.
self.assertEqual(
set([1]),
set(synapse.presynapticCell
for synapse in connections.synapsesForSegment(segments[1])))
# Verify the flatIdxs were properly reused.
self.assertLess(segment1.flatIdx, 2)
self.assertLess(segment3.flatIdx, 2)
self.assertTrue(
segment1 is connections.segmentForFlatIdx(segment1.flatIdx))
self.assertTrue(
segment3 is connections.segmentForFlatIdx(segment3.flatIdx))
def testPathsNotInvalidatedByOtherDestroys(self):
""" Creates segments and synapses, then destroys segments and synapses on
either side of them and verifies that existing Segment and Synapse
instances still point to the same segment / synapse as before.
"""
connections = Connections(1024)
segment1 = connections.createSegment(11)
connections.createSegment(12)
segment3 = connections.createSegment(13)
connections.createSegment(14)
segment5 = connections.createSegment(15)
synapse1 = connections.createSynapse(segment3, 201, .85)
synapse2 = connections.createSynapse(segment3, 202, .85)
synapse3 = connections.createSynapse(segment3, 203, .85)
synapse4 = connections.createSynapse(segment3, 204, .85)
synapse5 = connections.createSynapse(segment3, 205, .85)
self.assertEqual(203, synapse3.presynapticCell)
connections.destroySynapse(synapse1)
self.assertEqual(203, synapse3.presynapticCell)
connections.destroySynapse(synapse5)
self.assertEqual(203, synapse3.presynapticCell)
connections.destroySegment(segment1)
self.assertEqual(set([synapse2, synapse3, synapse4]),
connections.synapsesForSegment(segment3))
connections.destroySegment(segment5)
self.assertEqual(set([synapse2, synapse3, synapse4]),
connections.synapsesForSegment(segment3))
self.assertEqual(203, synapse3.presynapticCell)
def testPathsNotInvalidatedByOtherDestroys(self):
""" Creates segments and synapses, then destroys segments and synapses on
either side of them and verifies that existing Segment and Synapse
instances still point to the same segment / synapse as before.
"""
connections = Connections(1024)
segment1 = connections.createSegment(11)
connections.createSegment(12)
segment3 = connections.createSegment(13)
connections.createSegment(14)
segment5 = connections.createSegment(15)
synapse1 = connections.createSynapse(segment3, 201, .85)
synapse2 = connections.createSynapse(segment3, 202, .85)
synapse3 = connections.createSynapse(segment3, 203, .85)
synapse4 = connections.createSynapse(segment3, 204, .85)
synapse5 = connections.createSynapse(segment3, 205, .85)
self.assertEqual(203,
connections.dataForSynapse(synapse3).presynapticCell)
connections.destroySynapse(synapse1)
self.assertEqual(203,
connections.dataForSynapse(synapse3).presynapticCell)
connections.destroySynapse(synapse5)
self.assertEqual(203,
connections.dataForSynapse(synapse3).presynapticCell)
connections.destroySegment(segment1)
self.assertEqual(connections.synapsesForSegment(segment3),
[synapse2, synapse3, synapse4])
connections.destroySegment(segment5)
self.assertEqual(connections.synapsesForSegment(segment3),
[synapse2, synapse3, synapse4])
self.assertEqual(203,
connections.dataForSynapse(synapse3).presynapticCell)
def testCreateSegmentReuse(self):
connections = Connections(1024, 2)
segment1 = connections.createSegment(42)
connections.createSynapse(segment1, 1, .5)
connections.createSynapse(segment1, 2, .5)
connections.computeActivity([], .5, 2, .1, 1)
connections.computeActivity([], .5, 2, .1, 1)
connections.computeActivity([], .5, 2, .1, 1)
segment2 = connections.createSegment(42)
activeSegs, _ = connections.computeActivity([1, 2], .5, 2, .1, 1)
self.assertEqual(1, len(activeSegs))
self.assertEqual(segment1, activeSegs[0].segment)
segment3 = connections.createSegment(42)
self.assertEqual(segment2.idx, segment3.idx)
def testCreateSegmentReuse(self):
connections = Connections(1024, 2)
segment1 = connections.createSegment(42)
connections.createSynapse(segment1, 1, .5)
connections.createSynapse(segment1, 2, .5)
connections.computeActivity([], .5, 2, .1, 1)
connections.computeActivity([], .5, 2, .1, 1)
connections.computeActivity([], .5, 2, .1, 1)
segment2 = connections.createSegment(42)
activeSegs, _ = connections.computeActivity([1, 2], .5, 2, .1, 1)
self.assertEqual(1, len(activeSegs))
self.assertEqual(segment1, activeSegs[0].segment)
segment3 = connections.createSegment(42)
self.assertEqual(segment2.idx, segment3.idx)
def testCreateSegmentReuse(self):
connections = Connections(1024, 2)
segment1 = connections.createSegment(42)
connections.createSynapse(segment1, 1, .5)
connections.createSynapse(segment1, 2, .5)
# Let some time pass.
connections.startNewIteration();
connections.startNewIteration();
connections.startNewIteration();
# Create a segment with 3 synapse.
segment2 = connections.createSegment(42)
connections.createSynapse(segment2, 1, .5)
connections.createSynapse(segment2, 2, .5)
connections.createSynapse(segment2, 3, .5)
connections.startNewIteration();
# Give the first segment some activity.
connections.recordSegmentActivity(segment1)
# Create a new segment with 1 synapse.
segment3 = connections.createSegment(42);
connections.createSynapse(segment3, 1, .5)
segments = connections.segmentsForCell(42)
self.assertEqual(2, len(segments))
# Verify first segment is still there with the same synapses.
self.assertEqual(set([1, 2]),
set(synapse.presynapticCell for synapse in
connections.synapsesForSegment(segments[0])))
# Verify second segment has been replaced.
self.assertEqual(set([1]),
set(synapse.presynapticCell for synapse in
connections.synapsesForSegment(segments[1])))
# Verify the flatIdxs were properly reused.
self.assertLess(segment1.flatIdx, 2)
self.assertLess(segment3.flatIdx, 2)
self.assertTrue(segment1 is connections.segmentForFlatIdx(segment1.flatIdx))
self.assertTrue(segment3 is connections.segmentForFlatIdx(segment3.flatIdx))
def testCreateSegmentReuse(self):
connections = Connections(1024, 2)
segment1 = connections.createSegment(42)
connections.createSynapse(segment1, 1, .5)
connections.createSynapse(segment1, 2, .5)
# Let some time pass.
connections.startNewIteration()
connections.startNewIteration()
connections.startNewIteration()
segment2 = connections.createSegment(42)
connections.startNewIteration()
connections.recordSegmentActivity(segment1)
segment3 = connections.createSegment(42)
self.assertEqual(segment2.idx, segment3.idx)
def testCreateSegmentReuse(self):
connections = Connections(1024, 2)
segment1 = connections.createSegment(42)
connections.createSynapse(segment1, 1, .5)
connections.createSynapse(segment1, 2, .5)
# Let some time pass.
connections.startNewIteration();
connections.startNewIteration();
connections.startNewIteration();
segment2 = connections.createSegment(42)
connections.startNewIteration();
connections.recordSegmentActivity(segment1)
segment3 = connections.createSegment(42);
self.assertEqual(segment2.idx, segment3.idx)
def testUpdateSynapsePermanence(self):
""" Creates a synapse and updates its permanence, and makes sure that its
data was correctly updated.
"""
connections = Connections(1024)
segment = connections.createSegment(10)
synapse = connections.createSynapse(segment, 50, .34)
connections.updateSynapsePermanence(synapse, .21)
synapseData = connections.dataForSynapse(synapse)
self.assertAlmostEqual(synapseData.permanence, .21)
def testUpdateSynapsePermanence(self):
""" Creates a synapse and updates its permanence, and makes sure that its
data was correctly updated.
"""
connections = Connections(1024)
segment = connections.createSegment(10)
synapse = connections.createSynapse(segment, 50, .34)
connections.updateSynapsePermanence(synapse, .21)
synapseData = connections.dataForSynapse(synapse)
self.assertAlmostEqual(synapseData.permanence, .21)
def testReuseSegmentWithDestroyedSynapses(self):
""" Destroy a segment that has a destroyed synapse and a non-destroyed
synapse. Create a new segment in the same place. Make sure its synapse
count is correct.
"""
connections = Connections(1024)
segment = connections.createSegment(11)
synapse1 = connections.createSynapse(segment, 201, .85)
connections.createSynapse(segment, 202, .85)
connections.destroySynapse(synapse1)
self.assertEqual(1, connections.numSynapses(segment))
connections.destroySegment(segment)
reincarnated = connections.createSegment(11)
self.assertEqual(0, connections.numSynapses(reincarnated))
self.assertEqual(0, len(connections.synapsesForSegment(reincarnated)))
def testReuseSegmentWithDestroyedSynapses(self):
""" Destroy a segment that has a destroyed synapse and a non-destroyed
synapse. Create a new segment in the same place. Make sure its synapse
count is correct.
"""
connections = Connections(1024)
segment = connections.createSegment(11)
synapse1 = connections.createSynapse(segment, 201, .85)
connections.createSynapse(segment, 202, .85)
connections.destroySynapse(synapse1)
self.assertEqual(1, connections.numSynapses(segment))
connections.destroySegment(segment)
reincarnated = connections.createSegment(11)
self.assertEqual(0, connections.numSynapses(reincarnated))
self.assertEqual(0, len(connections.synapsesForSegment(reincarnated)))
def testReachSegmentLimitMultipleTimes(self):
""" Hit the maxSynapsesPerSegment threshold multiple times. Make sure it
works more than once.
"""
connections = Connections(1024, 2, 2)
segment = connections.createSegment(10)
connections.createSynapse(segment, 201, .85)
self.assertEqual(1, connections.numSynapses())
connections.createSynapse(segment, 202, .9)
self.assertEqual(2, connections.numSynapses())
connections.createSynapse(segment, 203, .8)
self.assertEqual(2, connections.numSynapses())
synapse = connections.createSynapse(segment, 204, .8)
self.assertEqual(2, connections.numSynapses())
def testReachSegmentLimitMultipleTimes(self):
""" Hit the maxSynapsesPerSegment threshold multiple times. Make sure it
works more than once.
"""
connections = Connections(1024, 2, 2)
segment = connections.createSegment(10)
connections.createSynapse(segment, 201, .85)
self.assertEqual(1, connections.numSynapses())
connections.createSynapse(segment, 202, .9)
self.assertEqual(2, connections.numSynapses())
connections.createSynapse(segment, 203, .8)
self.assertEqual(2, connections.numSynapses())
synapse = connections.createSynapse(segment, 204, .8)
self.assertEqual(2, connections.numSynapses())
def testDestroySynapse(self):
""" Creates a segment, creates a number of synapses on it, destroys a
synapse, and makes sure it got destroyed.
"""
connections = Connections(1024)
segment = connections.createSegment(20)
synapse1 = connections.createSynapse(segment, 80, .85)
synapse2 = connections.createSynapse(segment, 81, .85)
synapse3 = connections.createSynapse(segment, 82, .15)
self.assertEqual(3, connections.numSynapses())
connections.destroySynapse(synapse2)
self.assertEqual(2, connections.numSynapses())
self.assertEqual(connections.synapsesForSegment(segment), [synapse1,
synapse3])
active, matching = connections.computeActivity([80, 81, 82], .5, 2, 0.0, 1)
self.assertEqual(0, len(active))
self.assertEqual(1, len(matching))
self.assertEqual(2, matching[0].overlap)
def testSynapseReuse(self):
""" Creates a synapse over the synapses per segment limit, and verifies
that the lowest permanence synapse is removed to make room for the new
synapse.
"""
connections = Connections(1024, 1024, 2)
segment = connections.createSegment(10)
synapse1 = connections.createSynapse(segment, 50, .34)
synapse2 = connections.createSynapse(segment, 51, .34)
synapses = connections.synapsesForSegment(segment)
self.assertEqual(synapses, [synapse1, synapse2])
#Add an additional synapse to force it over the limit of num synapses
#per segment.
synapse3 = connections.createSynapse(segment, 52, .52)
self.assertEqual(0, synapse3.idx)
#ensure lower permanence synapse was removed
synapses = connections.synapsesForSegment(segment)
self.assertEqual(synapses, [synapse3, synapse2])
def testDestroySynapsesThenReachLimit(self):
""" Destroy some synapses then verify that the maxSynapsesPerSegment is
still correctly applied.
"""
connections = Connections(1024, 2, 2)
segment = connections.createSegment(10)
synapse1 = connections.createSynapse(segment, 201, .85)
synapse2 = connections.createSynapse(segment, 202, .85)
self.assertEqual(2, connections.numSynapses())
connections.destroySynapse(synapse1)
connections.destroySynapse(synapse2)
self.assertEqual(0, connections.numSynapses())
connections.createSynapse(segment, 201, .85)
self.assertEqual(1, connections.numSynapses())
connections.createSynapse(segment, 202, .90)
self.assertEqual(2, connections.numSynapses())
synapse3 = connections.createSynapse(segment, 203, .8)
self.assertEqual(2, connections.numSynapses())
def testDestroySynapsesThenReachLimit(self):
""" Destroy some synapses then verify that the maxSynapsesPerSegment is
still correctly applied.
"""
connections = Connections(1024, 2, 2)
segment = connections.createSegment(10)
synapse1 = connections.createSynapse(segment, 201, .85)
synapse2 = connections.createSynapse(segment, 202, .85)
self.assertEqual(2, connections.numSynapses())
connections.destroySynapse(synapse1)
connections.destroySynapse(synapse2)
self.assertEqual(0, connections.numSynapses())
connections.createSynapse(segment, 201, .85)
self.assertEqual(1, connections.numSynapses())
connections.createSynapse(segment, 202, .90)
self.assertEqual(2, connections.numSynapses())
synapse3 = connections.createSynapse(segment, 203, .8)
self.assertEqual(2, connections.numSynapses())
def testSynapseReuse(self):
""" Creates a synapse over the synapses per segment limit, and verifies
that the lowest permanence synapse is removed to make room for the new
synapse.
"""
connections = Connections(1024, 1024, 2)
segment = connections.createSegment(10)
synapse1 = connections.createSynapse(segment, 50, .34)
synapse2 = connections.createSynapse(segment, 51, .34)
synapses = connections.synapsesForSegment(segment)
self.assertEqual(synapses, [synapse1, synapse2])
#Add an additional synapse to force it over the limit of num synapses
#per segment.
synapse3 = connections.createSynapse(segment, 52, .52)
self.assertEqual(0, synapse3.idx)
#ensure lower permanence synapse was removed
synapses = connections.synapsesForSegment(segment)
self.assertEqual(synapses, [synapse3, synapse2])
def testSynapseReuse(self):
""" Creates a synapse over the synapses per segment limit, and verifies
that the lowest permanence synapse is removed to make room for the new
synapse.
"""
connections = Connections(1024, 1024, 2)
segment = connections.createSegment(10)
synapse1 = connections.createSynapse(segment, 50, .34)
synapse2 = connections.createSynapse(segment, 51, .48)
synapses = connections.synapsesForSegment(segment)
self.assertEqual(set([synapse1, synapse2]), synapses)
# Add an additional synapse to force it over the limit of num synapses
# per segment.
connections.createSynapse(segment, 52, .52)
# Ensure lower permanence synapse was removed.
self.assertEqual(set([51, 52]),
set(synapse.presynapticCell
for synapse in
connections.synapsesForSegment(segment)))
def testDestroySynapse(self):
""" Creates a segment, creates a number of synapses on it, destroys a
synapse, and makes sure it got destroyed.
"""
connections = Connections(1024)
segment = connections.createSegment(20)
synapse1 = connections.createSynapse(segment, 80, .85)
synapse2 = connections.createSynapse(segment, 81, .85)
synapse3 = connections.createSynapse(segment, 82, .15)
self.assertEqual(3, connections.numSynapses())
connections.destroySynapse(synapse2)
self.assertEqual(2, connections.numSynapses())
self.assertEqual(set([synapse1, synapse3]),
connections.synapsesForSegment(segment))
(numActiveConnected,
numActivePotential) = connections.computeActivity([80, 81, 82], .5)
self.assertEqual(1, numActiveConnected[segment.flatIdx])
self.assertEqual(2, numActivePotential[segment.flatIdx])
def testDestroySynapse(self):
""" Creates a segment, creates a number of synapses on it, destroys a
synapse, and makes sure it got destroyed.
"""
connections = Connections(1024)
segment = connections.createSegment(20)
synapse1 = connections.createSynapse(segment, 80, .85)
synapse2 = connections.createSynapse(segment, 81, .85)
synapse3 = connections.createSynapse(segment, 82, .15)
self.assertEqual(3, connections.numSynapses())
connections.destroySynapse(synapse2)
self.assertEqual(2, connections.numSynapses())
self.assertEqual(set([synapse1, synapse3]),
connections.synapsesForSegment(segment))
(numActiveConnected,
numActivePotential) = connections.computeActivity([80, 81, 82], .5)
self.assertEqual(1, numActiveConnected[segment.flatIdx])
self.assertEqual(2, numActivePotential[segment.flatIdx])
def testDestroySynapse(self):
""" Creates a segment, creates a number of synapses on it, destroys a
synapse, and makes sure it got destroyed.
"""
connections = Connections(1024)
segment = connections.createSegment(20)
synapse1 = connections.createSynapse(segment, 80, .85)
synapse2 = connections.createSynapse(segment, 81, .85)
synapse3 = connections.createSynapse(segment, 82, .15)
self.assertEqual(3, connections.numSynapses())
connections.destroySynapse(synapse2)
self.assertEqual(2, connections.numSynapses())
self.assertEqual(connections.synapsesForSegment(segment),
[synapse1, synapse3])
active, matching = connections.computeActivity([80, 81, 82], .5, 2,
0.0, 1)
self.assertEqual(0, len(active))
self.assertEqual(1, len(matching))
self.assertEqual(2, matching[0].overlap)
def testSynapseReuse(self):
""" Creates a synapse over the synapses per segment limit, and verifies
that the lowest permanence synapse is removed to make room for the new
synapse.
"""
connections = Connections(1024, 1024, 2)
segment = connections.createSegment(10)
synapse1 = connections.createSynapse(segment, 50, .34)
synapse2 = connections.createSynapse(segment, 51, .48)
synapses = connections.synapsesForSegment(segment)
self.assertEqual(set([synapse1, synapse2]), synapses)
# Add an additional synapse to force it over the limit of num synapses
# per segment.
connections.createSynapse(segment, 52, .52)
# Ensure lower permanence synapse was removed.
self.assertEqual(
set([51, 52]),
set(synapse.presynapticCell
for synapse in connections.synapsesForSegment(segment)))
def testDestroySegmentWithDestroyedSynapses(self):
""" Destroy a segment that has a destroyed synapse and a non-destroyed
synapse. Make sure nothing gets double-destroyed.
"""
connections = Connections(1024)
segment1 = connections.createSegment(11)
segment2 = connections.createSegment(12)
connections.createSynapse(segment1, 101, .85)
synapse2a = connections.createSynapse(segment2, 201, .85)
connections.createSynapse(segment2, 202, .85)
self.assertEqual(3, connections.numSynapses())
connections.destroySynapse(synapse2a)
self.assertEqual(2, connections.numSegments())
self.assertEqual(2, connections.numSynapses())
connections.destroySegment(segment2)
self.assertEqual(1, connections.numSegments())
self.assertEqual(1, connections.numSynapses())
def testDestroySegmentWithDestroyedSynapses(self):
""" Destroy a segment that has a destroyed synapse and a non-destroyed
synapse. Make sure nothing gets double-destroyed.
"""
connections = Connections(1024)
segment1 = connections.createSegment(11)
segment2 = connections.createSegment(12)
connections.createSynapse(segment1, 101, .85)
synapse2a = connections.createSynapse(segment2, 201, .85)
connections.createSynapse(segment2, 202, .85)
self.assertEqual(3, connections.numSynapses())
connections.destroySynapse(synapse2a)
self.assertEqual(2, connections.numSegments())
self.assertEqual(2, connections.numSynapses())
connections.destroySegment(segment2)
self.assertEqual(1, connections.numSegments())
self.assertEqual(1, connections.numSynapses())
def testDestroySegmentsThenReachLimit(self):
""" Destroy some segments then verify that the maxSegmentsPerCell is still
correctly applied.
"""
connections = Connections(1024, 2, 2)
segment1 = connections.createSegment(11)
segment2 = connections.createSegment(11)
self.assertEqual(2, connections.numSegments())
connections.destroySegment(segment1)
connections.destroySegment(segment2)
self.assertEqual(0, connections.numSegments())
connections.createSegment(11)
self.assertEqual(1, connections.numSegments())
connections.createSegment(11)
self.assertEqual(2, connections.numSegments())
segment3 = connections.createSegment(11)
self.assertEqual(2, connections.numSegments(11))
self.assertEqual(2, connections.numSegments())
def testDestroySegmentsThenReachLimit(self):
""" Destroy some segments then verify that the maxSegmentsPerCell is still
correctly applied.
"""
connections = Connections(1024, 2, 2)
segment1 = connections.createSegment(11)
segment2 = connections.createSegment(11)
self.assertEqual(2, connections.numSegments())
connections.destroySegment(segment1)
connections.destroySegment(segment2)
self.assertEqual(0, connections.numSegments())
connections.createSegment(11)
self.assertEqual(1, connections.numSegments())
connections.createSegment(11)
self.assertEqual(2, connections.numSegments())
segment3 = connections.createSegment(11)
self.assertLess(segment3.idx, 2)
self.assertEqual(2, connections.numSegments())
class TemporalMemory(object):
"""
Class implementing the Temporal Memory algorithm.
"""
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):
"""
@param columnDimensions (list) Dimensions of the column space
@param cellsPerColumn (int) Number of cells per column
@param activationThreshold (int) If the number of active connected synapses on a segment is at least this threshold, the segment is said to be active.
@param initialPermanence (float) Initial permanence of a new synapse.
@param connectedPermanence (float) If the permanence value for a synapse is greater than this value, it is said to be connected.
@param minThreshold (int) If the number of synapses active on a segment is at least this threshold, it is selected as the best matching cell in a bursting column.
@param maxNewSynapseCount (int) The maximum number of synapses added to a segment during learning.
@param permanenceIncrement (float) Amount by which permanences of synapses are incremented during learning.
@param permanenceDecrement (float) Amount by which permanences of synapses are decremented during learning.
@param predictedSegmentDecrement (float) Amount by which active permanences of synapses of previously predicted but inactive segments are decremented.
@param seed (int) Seed for the random number generator.
Notes:
predictedSegmentDecrement: A good value is just a bit larger than
(the column-level sparsity * permanenceIncrement). So, if column-level
sparsity is 2% and permanenceIncrement is 0.01, this parameter should be
something like 4% * 0.01 = 0.0004).
"""
# Error checking
if not len(columnDimensions):
raise ValueError(
"Number of column dimensions must be greater than 0")
if not cellsPerColumn > 0:
raise ValueError(
"Number of cells per column must be greater than 0")
# TODO: Validate all parameters (and add validation tests)
# Save member variables
self.columnDimensions = 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
# Initialize member variables
self.connections = Connections(self.numberOfCells())
self._random = Random(seed)
self.activeCells = set()
self.predictiveCells = set()
self.activeSegments = set()
self.winnerCells = set()
self.matchingSegments = set()
self.matchingCells = set()
# ==============================
# Main functions
# ==============================
def compute(self, activeColumns, learn=True):
"""
Feeds input record through TM, performing inference and learning.
@param activeColumns (set) Indices of active columns
@param learn (bool) Whether or not learning is enabled
Updates member variables:
- `activeCells` (set)
- `winnerCells` (set)
- `activeSegments` (set)
- `predictiveCells` (set)
- `matchingSegments`(set)
- `matchingCells` (set)
- `connections` (Connections)
"""
prevPredictiveCells = self.predictiveCells
prevActiveSegments = self.activeSegments
prevActiveCells = self.activeCells
prevWinnerCells = self.winnerCells
prevMatchingSegments = self.matchingSegments
prevMatchingCells = self.matchingCells
activeCells = set()
winnerCells = set()
(_activeCells, _winnerCells, predictedActiveColumns,
predictedInactiveCells) = self.activateCorrectlyPredictiveCells(
prevPredictiveCells, prevMatchingCells, activeColumns)
activeCells.update(_activeCells)
winnerCells.update(_winnerCells)
(_activeCells, _winnerCells, learningSegments) = self.burstColumns(
activeColumns, predictedActiveColumns, prevActiveCells,
prevWinnerCells)
activeCells.update(_activeCells)
winnerCells.update(_winnerCells)
if learn:
self.learnOnSegments(prevActiveSegments, learningSegments,
prevActiveCells, winnerCells, prevWinnerCells,
predictedInactiveCells, prevMatchingSegments)
(activeSegments, predictiveCells, matchingSegments,
matchingCells) = self.computePredictiveCells(activeCells)
self.activeCells = activeCells
self.winnerCells = winnerCells
self.activeSegments = activeSegments
self.predictiveCells = predictiveCells
self.matchingSegments = matchingSegments
self.matchingCells = matchingCells
def reset(self):
"""
Indicates the start of a new sequence. Resets sequence state of the TM.
"""
self.activeCells = set()
self.predictiveCells = set()
self.activeSegments = set()
self.winnerCells = set()
# ==============================
# Phases
# ==============================
def activateCorrectlyPredictiveCells(self, prevPredictiveCells,
prevMatchingCells, activeColumns):
"""
Phase 1: Activate the correctly predictive cells.
Pseudocode:
- for each prev predictive cell
- if in active column
- mark it as active
- mark it as winner cell
- mark column as predicted => active
- if not in active column
- mark it as an predicted but inactive cell
@param prevPredictiveCells (set) Indices of predictive cells in `t-1`
@param activeColumns (set) Indices of active columns in `t`
@return (tuple) Contains:
`activeCells` (set),
`winnerCells` (set),
`predictedActiveColumns` (set),
`predictedInactiveCells` (set)
"""
activeCells = set()
winnerCells = set()
predictedActiveColumns = set()
predictedInactiveCells = set()
for cell in prevPredictiveCells:
column = self.columnForCell(cell)
if column in activeColumns:
activeCells.add(cell)
winnerCells.add(cell)
predictedActiveColumns.add(column)
if self.predictedSegmentDecrement > 0:
for cell in prevMatchingCells:
column = self.columnForCell(cell)
if column not in activeColumns:
predictedInactiveCells.add(cell)
return (activeCells, winnerCells, predictedActiveColumns,
predictedInactiveCells)
def burstColumns(self, activeColumns, predictedActiveColumns,
prevActiveCells, prevWinnerCells):
"""
Phase 2: Burst unpredicted columns.
Pseudocode:
- for each unpredicted active column
- mark all cells as active
- mark the best matching cell as winner cell
- (learning)
- if it has no matching segment
- (optimization) if there are prev winner cells
- add a segment to it
- mark the segment as learning
@param activeColumns (set) Indices of active columns in `t`
@param predictedActiveColumns (set) Indices of predicted => active columns in `t`
@param prevActiveCells (set) Indices of active cells in `t-1`
@param prevWinnerCells (set) Indices of winner cells in `t-1`
@return (tuple) Contains:
`activeCells` (set),
`winnerCells` (set),
`learningSegments` (set)
"""
activeCells = set()
winnerCells = set()
learningSegments = set()
unpredictedActiveColumns = activeColumns - predictedActiveColumns
for column in unpredictedActiveColumns:
cells = self.cellsForColumn(column)
activeCells.update(cells)
(bestCell,
bestSegment) = self.bestMatchingCell(cells, prevActiveCells)
winnerCells.add(bestCell)
if bestSegment is None and len(prevWinnerCells):
bestSegment = self.connections.createSegment(bestCell)
if bestSegment is not None:
learningSegments.add(bestSegment)
return activeCells, winnerCells, learningSegments
def learnOnSegments(self, prevActiveSegments, learningSegments,
prevActiveCells, winnerCells, prevWinnerCells,
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
- if predictedSegmentDecrement > 0
- for each previously matching segment
- if cell is a predicted inactive cell
- weaken active synapses but don't touch inactive synapses
@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 prevWinnerCells (set) Indices of winner cells in `t-1`
@param predictedInactiveCells (set) Indices of predicted inactive cells
@param prevMatchingSegments (set) Indices of segments with
"""
for segment in prevActiveSegments | learningSegments:
isLearningSegment = segment in learningSegments
isFromWinnerCell = self.connections.cellForSegment(
segment) in winnerCells
activeSynapses = self.activeSynapsesForSegment(
segment, prevActiveCells)
if isLearningSegment or isFromWinnerCell:
self.adaptSegment(segment, activeSynapses,
self.permanenceIncrement,
self.permanenceDecrement)
if isLearningSegment:
n = self.maxNewSynapseCount - len(activeSynapses)
for presynapticCell in self.pickCellsToLearnOn(
n, segment, prevWinnerCells):
self.connections.createSynapse(segment, presynapticCell,
self.initialPermanence)
if self.predictedSegmentDecrement > 0:
for segment in prevMatchingSegments:
isPredictedInactiveCell = (
self.connections.cellForSegment(segment)
in predictedInactiveCells)
activeSynapses = self.activeSynapsesForSegment(
segment, prevActiveCells)
if isPredictedInactiveCell:
self.adaptSegment(segment, activeSynapses,
-self.predictedSegmentDecrement, 0.0)
def computePredictiveCells(self, activeCells):
"""
Phase 4: Compute predictive cells due to lateral input
on distal dendrites.
Pseudocode:
- for each distal dendrite segment with activity >= activationThreshold
- mark the segment as active
- mark the cell as predictive
- if predictedSegmentDecrement > 0
- for each distal dendrite segment with unconnected
activity >= minThreshold
- mark the segment as matching
- mark the cell as matching
Forward propagates activity from active cells to the synapses that touch
them, to determine which synapses are active.
@param activeCells (set) Indices of active cells in `t`
@return (tuple) Contains:
`activeSegments` (set),
`predictiveCells` (set),
`matchingSegments` (set),
`matchingCells` (set)
"""
numActiveConnectedSynapsesForSegment = defaultdict(int)
numActiveSynapsesForSegment = defaultdict(int)
activeSegments = set()
predictiveCells = set()
matchingSegments = set()
matchingCells = set()
for cell in activeCells:
synapses = self.connections.synapsesForPresynapticCell(cell)
for synapseData in synapses.values():
segment = synapseData.segment
permanence = synapseData.permanence
if permanence >= self.connectedPermanence:
numActiveConnectedSynapsesForSegment[segment] += 1
if (numActiveConnectedSynapsesForSegment[segment] >=
self.activationThreshold):
activeSegments.add(segment)
predictiveCells.add(
self.connections.cellForSegment(segment))
if permanence > 0 and self.predictedSegmentDecrement > 0:
numActiveSynapsesForSegment[segment] += 1
if numActiveSynapsesForSegment[
segment] >= self.minThreshold:
matchingSegments.add(segment)
matchingCells.add(
self.connections.cellForSegment(segment))
return activeSegments, predictiveCells, matchingSegments, matchingCells
# ==============================
# Helper functions
# ==============================
def bestMatchingCell(self, cells, activeCells):
"""
Gets the cell with the best matching segment
(see `TM.bestMatchingSegment`) that has the largest number of active
synapses of all best matching segments.
If none were found, pick the least used cell (see `TM.leastUsedCell`).
@param cells (set) Indices of cells
@param activeCells (set) Indices of active cells
@return (tuple) Contains:
`cell` (int),
`bestSegment` (int)
"""
maxSynapses = 0
bestCell = None
bestSegment = None
for cell in cells:
segment, numActiveSynapses = self.bestMatchingSegment(
cell, activeCells)
if segment is not None and numActiveSynapses > maxSynapses:
maxSynapses = numActiveSynapses
bestCell = cell
bestSegment = segment
if bestCell is None:
bestCell = self.leastUsedCell(cells)
return bestCell, bestSegment
def bestMatchingSegment(self, cell, activeCells):
"""
Gets the segment on a cell with the largest number of activate synapses,
including all synapses with non-zero permanences.
@param cell (int) Cell index
@param activeCells (set) Indices of active cells
@return (tuple) Contains:
`segment` (int),
`connectedActiveSynapses` (set)
"""
maxSynapses = self.minThreshold
bestSegment = None
bestNumActiveSynapses = None
for segment in self.connections.segmentsForCell(cell):
numActiveSynapses = 0
for synapse in self.connections.synapsesForSegment(segment):
synapseData = self.connections.dataForSynapse(synapse)
if ((synapseData.presynapticCell in activeCells)
and synapseData.permanence > 0):
numActiveSynapses += 1
if numActiveSynapses >= maxSynapses:
maxSynapses = numActiveSynapses
bestSegment = segment
bestNumActiveSynapses = numActiveSynapses
return bestSegment, bestNumActiveSynapses
def leastUsedCell(self, cells):
"""
Gets the cell with the smallest number of segments.
Break ties randomly.
@param cells (set) Indices of cells
@return (int) Cell index
"""
leastUsedCells = set()
minNumSegments = float("inf")
for cell in cells:
numSegments = len(self.connections.segmentsForCell(cell))
if numSegments < minNumSegments:
minNumSegments = numSegments
leastUsedCells = set()
if numSegments == minNumSegments:
leastUsedCells.add(cell)
i = self._random.getUInt32(len(leastUsedCells))
return sorted(leastUsedCells)[i]
def activeSynapsesForSegment(self, segment, activeCells):
"""
Returns the synapses on a segment that are active due to lateral input
from active cells.
@param segment (int) Segment index
@param activeCells (set) Indices of active cells
@return (set) Indices of active synapses on segment
"""
synapses = set()
for synapse in self.connections.synapsesForSegment(segment):
synapseData = self.connections.dataForSynapse(synapse)
if synapseData.presynapticCell in activeCells:
synapses.add(synapse)
return synapses
def adaptSegment(self, segment, activeSynapses, permanenceIncrement,
permanenceDecrement):
"""
Updates synapses on segment.
Strengthens active synapses; weakens inactive synapses.
@param segment (int) Segment index
@param activeSynapses (set) Indices of active synapses
@param permanenceIncrement (float) Amount to increment active synapses
@param permanenceDecrement (float) Amount to decrement inactive synapses
"""
# Need to copy synapses for segment set below because it will be modified
# during iteration by `destroySynapse`
for synapse in set(self.connections.synapsesForSegment(segment)):
synapseData = self.connections.dataForSynapse(synapse)
permanence = synapseData.permanence
if synapse in activeSynapses:
permanence += permanenceIncrement
else:
permanence -= permanenceDecrement
# Keep permanence within min/max bounds
permanence = max(0.0, min(1.0, permanence))
if (abs(permanence) < EPSILON):
self.connections.destroySynapse(synapse)
else:
self.connections.updateSynapsePermanence(synapse, permanence)
def pickCellsToLearnOn(self, n, segment, winnerCells):
"""
Pick cells to form distal connections to.
TODO: Respect topology and learningRadius
@param n (int) Number of cells to pick
@param segment (int) Segment index
@param winnerCells (set) Indices of winner cells in `t`
@return (set) Indices of cells picked
"""
candidates = set(winnerCells)
# Remove cells that are already synapsed on by this segment
for synapse in self.connections.synapsesForSegment(segment):
synapseData = self.connections.dataForSynapse(synapse)
presynapticCell = synapseData.presynapticCell
if presynapticCell in candidates:
candidates.remove(presynapticCell)
n = min(n, len(candidates))
candidates = sorted(candidates)
cells = set()
# Pick n cells randomly
for _ in range(n):
i = self._random.getUInt32(len(candidates))
cells.add(candidates[i])
del candidates[i]
return cells
def columnForCell(self, cell):
"""
Returns the index of the column that a cell belongs to.
@param cell (int) Cell index
@return (int) Column index
"""
self._validateCell(cell)
return int(cell / self.cellsPerColumn)
def cellsForColumn(self, column):
"""
Returns the indices of cells that belong to a column.
@param column (int) Column index
@return (set) Cell indices
"""
self._validateColumn(column)
start = self.cellsPerColumn * self.getCellIndex(column)
end = start + self.cellsPerColumn
return set(xrange(start, end))
def numberOfColumns(self):
"""
Returns the number of columns in this layer.
@return (int) Number of columns
"""
return reduce(mul, self.columnDimensions, 1)
def numberOfCells(self):
"""
Returns the number of cells in this layer.
@return (int) Number of cells
"""
return self.numberOfColumns() * self.cellsPerColumn
def mapCellsToColumns(self, cells):
"""
Maps cells to the columns they belong to
@param cells (set) Cells
@return (dict) Mapping from columns to their cells in `cells`
"""
cellsForColumns = defaultdict(set)
for cell in cells:
column = self.columnForCell(cell)
cellsForColumns[column].add(cell)
return cellsForColumns
def write(self, proto):
"""
Writes serialized data to proto object
@param proto (DynamicStructBuilder) Proto object
"""
proto.columnDimensions = self.columnDimensions
proto.cellsPerColumn = self.cellsPerColumn
proto.activationThreshold = self.activationThreshold
proto.initialPermanence = self.initialPermanence
proto.connectedPermanence = self.connectedPermanence
proto.minThreshold = self.minThreshold
proto.maxNewSynapseCount = self.maxNewSynapseCount
proto.permanenceIncrement = self.permanenceIncrement
proto.permanenceDecrement = self.permanenceDecrement
proto.predictedSegmentDecrement = self.predictedSegmentDecrement
self.connections.write(proto.connections)
self._random.write(proto.random)
proto.activeCells = list(self.activeCells)
proto.predictiveCells = list(self.predictiveCells)
proto.activeSegments = list(self.activeSegments)
proto.winnerCells = list(self.winnerCells)
proto.matchingSegments = list(self.matchingSegments)
proto.matchingCells = list(self.matchingCells)
@classmethod
def read(cls, proto):
"""
Reads deserialized data from proto object
@param proto (DynamicStructBuilder) Proto object
@return (TemporalMemory) TemporalMemory instance
"""
tm = object.__new__(cls)
tm.columnDimensions = list(proto.columnDimensions)
tm.cellsPerColumn = int(proto.cellsPerColumn)
tm.activationThreshold = int(proto.activationThreshold)
tm.initialPermanence = proto.initialPermanence
tm.connectedPermanence = proto.connectedPermanence
tm.minThreshold = int(proto.minThreshold)
tm.maxNewSynapseCount = int(proto.maxNewSynapseCount)
tm.permanenceIncrement = proto.permanenceIncrement
tm.permanenceDecrement = proto.permanenceDecrement
tm.predictedSegmentDecrement = proto.predictedSegmentDecrement
tm.connections = Connections.read(proto.connections)
tm._random = Random()
tm._random.read(proto.random)
tm.activeCells = set([int(x) for x in proto.activeCells])
tm.predictiveCells = set([int(x) for x in proto.predictiveCells])
tm.activeSegments = set([int(x) for x in proto.activeSegments])
tm.winnerCells = set([int(x) for x in proto.winnerCells])
tm.matchingSegments = set([int(x) for x in proto.matchingSegments])
tm.matchingCells = set([int(x) for x in proto.matchingCells])
return tm
def __eq__(self, other):
"""
Equality operator for TemporalMemory instances.
Checks if two instances are functionally identical
(might have different internal state).
@param other (TemporalMemory) TemporalMemory instance to compare to
"""
if self.columnDimensions != other.columnDimensions: return False
if self.cellsPerColumn != other.cellsPerColumn: return False
if self.activationThreshold != other.activationThreshold: return False
if abs(self.initialPermanence - other.initialPermanence) > EPSILON:
return False
if abs(self.connectedPermanence - other.connectedPermanence) > EPSILON:
return False
if self.minThreshold != other.minThreshold: return False
if self.maxNewSynapseCount != other.maxNewSynapseCount: return False
if abs(self.permanenceIncrement - other.permanenceIncrement) > EPSILON:
return False
if abs(self.permanenceDecrement - other.permanenceDecrement) > EPSILON:
return False
if abs(self.predictedSegmentDecrement -
other.predictedSegmentDecrement) > EPSILON:
return False
if self.connections != other.connections: return False
if self.activeCells != other.activeCells: return False
if self.predictiveCells != other.predictiveCells: return False
if self.winnerCells != other.winnerCells: return False
if self.matchingSegments != other.matchingSegments: return False
if self.matchingCells != other.matchingCells: return False
return True
def __ne__(self, other):
"""
Non-equality operator for TemporalMemory instances.
Checks if two instances are not functionally identical
(might have different internal state).
@param other (TemporalMemory) TemporalMemory instance to compare to
"""
return not self.__eq__(other)
def _validateColumn(self, column):
"""
Raises an error if column index is invalid.
@param column (int) Column index
"""
if column >= self.numberOfColumns() or column < 0:
raise IndexError("Invalid column")
def _validateCell(self, cell):
"""
Raises an error if cell index is invalid.
@param cell (int) Cell index
"""
if cell >= self.numberOfCells() or cell < 0:
raise IndexError("Invalid cell")
@classmethod
def getCellIndices(cls, cells):
return [cls.getCellIndex(c) for c in cells]
@staticmethod
def getCellIndex(cell):
return cell
class TemporalMemory(object):
"""
Class implementing the Temporal Memory algorithm.
"""
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):
"""
@param columnDimensions (list) Dimensions of the column space
@param cellsPerColumn (int) Number of cells per column
@param activationThreshold (int) If the number of active connected synapses on a segment is at least this threshold, the segment is said to be active.
@param initialPermanence (float) Initial permanence of a new synapse.
@param connectedPermanence (float) If the permanence value for a synapse is greater than this value, it is said to be connected.
@param minThreshold (int) If the number of synapses active on a segment is at least this threshold, it is selected as the best matching cell in a bursting column.
@param maxNewSynapseCount (int) The maximum number of synapses added to a segment during learning.
@param permanenceIncrement (float) Amount by which permanences of synapses are incremented during learning.
@param permanenceDecrement (float) Amount by which permanences of synapses are decremented during learning.
@param predictedSegmentDecrement (float) Amount by which active permanences of synapses of previously predicted but inactive segments are decremented.
@param seed (int) Seed for the random number generator.
Notes:
predictedSegmentDecrement: A good value is just a bit larger than
(the column-level sparsity * permanenceIncrement). So, if column-level
sparsity is 2% and permanenceIncrement is 0.01, this parameter should be
something like 4% * 0.01 = 0.0004).
"""
# Error checking
if not len(columnDimensions):
raise ValueError("Number of column dimensions must be greater than 0")
if not cellsPerColumn > 0:
raise ValueError("Number of cells per column must be greater than 0")
# TODO: Validate all parameters (and add validation tests)
# Save member variables
self.columnDimensions = 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
# Initialize member variables
self.connections = Connections(self.numberOfCells())
self._random = Random(seed)
self.activeCells = set()
self.predictiveCells = set()
self.activeSegments = set()
self.winnerCells = set()
self.matchingSegments = set()
self.matchingCells = set()
# ==============================
# Main functions
# ==============================
def compute(self, activeColumns, learn=True):
"""
Feeds input record through TM, performing inference and learning.
@param activeColumns (set) Indices of active columns
@param learn (bool) Whether or not learning is enabled
Updates member variables:
- `activeCells` (set)
- `winnerCells` (set)
- `activeSegments` (set)
- `predictiveCells` (set)
- `matchingSegments`(set)
- `matchingCells` (set)
- `connections` (Connections)
"""
prevPredictiveCells = self.predictiveCells
prevActiveSegments = self.activeSegments
prevActiveCells = self.activeCells
prevWinnerCells = self.winnerCells
prevMatchingSegments = self.matchingSegments
prevMatchingCells = self.matchingCells
activeCells = set()
winnerCells = set()
(_activeCells,
_winnerCells,
predictedActiveColumns,
predictedInactiveCells) = self.activateCorrectlyPredictiveCells(
prevPredictiveCells,
prevMatchingCells,
activeColumns)
activeCells.update(_activeCells)
winnerCells.update(_winnerCells)
(_activeCells,
_winnerCells,
learningSegments) = self.burstColumns(activeColumns,
predictedActiveColumns,
prevActiveCells,
prevWinnerCells)
activeCells.update(_activeCells)
winnerCells.update(_winnerCells)
if learn:
self.learnOnSegments(prevActiveSegments,
learningSegments,
prevActiveCells,
winnerCells,
prevWinnerCells,
predictedInactiveCells,
prevMatchingSegments)
(activeSegments,
predictiveCells,
matchingSegments,
matchingCells) = self.computePredictiveCells(activeCells)
self.activeCells = activeCells
self.winnerCells = winnerCells
self.activeSegments = activeSegments
self.predictiveCells = predictiveCells
self.matchingSegments = matchingSegments
self.matchingCells = matchingCells
def reset(self):
"""
Indicates the start of a new sequence. Resets sequence state of the TM.
"""
self.activeCells = set()
self.predictiveCells = set()
self.activeSegments = set()
self.winnerCells = set()
# ==============================
# Phases
# ==============================
def activateCorrectlyPredictiveCells(self,
prevPredictiveCells,
prevMatchingCells,
activeColumns):
"""
Phase 1: Activate the correctly predictive cells.
Pseudocode:
- for each prev predictive cell
- if in active column
- mark it as active
- mark it as winner cell
- mark column as predicted => active
- if not in active column
- mark it as an predicted but inactive cell
@param prevPredictiveCells (set) Indices of predictive cells in `t-1`
@param activeColumns (set) Indices of active columns in `t`
@return (tuple) Contains:
`activeCells` (set),
`winnerCells` (set),
`predictedActiveColumns` (set),
`predictedInactiveCells` (set)
"""
activeCells = set()
winnerCells = set()
predictedActiveColumns = set()
predictedInactiveCells = set()
for cell in prevPredictiveCells:
column = self.columnForCell(cell)
if column in activeColumns:
activeCells.add(cell)
winnerCells.add(cell)
predictedActiveColumns.add(column)
if self.predictedSegmentDecrement > 0:
for cell in prevMatchingCells:
column = self.columnForCell(cell)
if column not in activeColumns:
predictedInactiveCells.add(cell)
return (activeCells,
winnerCells,
predictedActiveColumns,
predictedInactiveCells)
def burstColumns(self,
activeColumns,
predictedActiveColumns,
prevActiveCells,
prevWinnerCells):
"""
Phase 2: Burst unpredicted columns.
Pseudocode:
- for each unpredicted active column
- mark all cells as active
- mark the best matching cell as winner cell
- (learning)
- if it has no matching segment
- (optimization) if there are prev winner cells
- add a segment to it
- mark the segment as learning
@param activeColumns (set) Indices of active columns in `t`
@param predictedActiveColumns (set) Indices of predicted => active columns in `t`
@param prevActiveCells (set) Indices of active cells in `t-1`
@param prevWinnerCells (set) Indices of winner cells in `t-1`
@return (tuple) Contains:
`activeCells` (set),
`winnerCells` (set),
`learningSegments` (set)
"""
activeCells = set()
winnerCells = set()
learningSegments = set()
unpredictedActiveColumns = activeColumns - predictedActiveColumns
for column in unpredictedActiveColumns:
cells = self.cellsForColumn(column)
activeCells.update(cells)
(bestCell,
bestSegment) = self.bestMatchingCell(cells, prevActiveCells)
winnerCells.add(bestCell)
if bestSegment is None and len(prevWinnerCells):
bestSegment = self.connections.createSegment(bestCell)
if bestSegment is not None:
learningSegments.add(bestSegment)
return activeCells, winnerCells, learningSegments
def learnOnSegments(self,
prevActiveSegments,
learningSegments,
prevActiveCells,
winnerCells,
prevWinnerCells,
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
- if predictedSegmentDecrement > 0
- for each previously matching segment
- if cell is a predicted inactive cell
- weaken active synapses but don't touch inactive synapses
@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 prevWinnerCells (set) Indices of winner cells in `t-1`
@param predictedInactiveCells (set) Indices of predicted inactive cells
@param prevMatchingSegments (set) Indices of segments with
"""
for segment in prevActiveSegments | learningSegments:
isLearningSegment = segment in learningSegments
isFromWinnerCell = self.connections.cellForSegment(segment) in winnerCells
activeSynapses = self.activeSynapsesForSegment(segment, prevActiveCells)
if isLearningSegment or isFromWinnerCell:
self.adaptSegment(segment,
activeSynapses,
self.permanenceIncrement,
self.permanenceDecrement)
if isLearningSegment:
n = self.maxNewSynapseCount - len(activeSynapses)
for presynapticCell in self.pickCellsToLearnOn(n,
segment,
prevWinnerCells):
self.connections.createSynapse(segment,
presynapticCell,
self.initialPermanence)
if self.predictedSegmentDecrement > 0:
for segment in prevMatchingSegments:
isPredictedInactiveCell = (self.connections.cellForSegment(segment) in
predictedInactiveCells)
activeSynapses = self.activeSynapsesForSegment(segment, prevActiveCells)
if isPredictedInactiveCell:
self.adaptSegment(segment,
activeSynapses,
-self.predictedSegmentDecrement,
0.0)
def computePredictiveCells(self, activeCells):
"""
Phase 4: Compute predictive cells due to lateral input
on distal dendrites.
Pseudocode:
- for each distal dendrite segment with activity >= activationThreshold
- mark the segment as active
- mark the cell as predictive
- if predictedSegmentDecrement > 0
- for each distal dendrite segment with unconnected
activity >= minThreshold
- mark the segment as matching
- mark the cell as matching
Forward propagates activity from active cells to the synapses that touch
them, to determine which synapses are active.
@param activeCells (set) Indices of active cells in `t`
@return (tuple) Contains:
`activeSegments` (set),
`predictiveCells` (set),
`matchingSegments` (set),
`matchingCells` (set)
"""
numActiveConnectedSynapsesForSegment = defaultdict(int)
numActiveSynapsesForSegment = defaultdict(int)
activeSegments = set()
predictiveCells = set()
matchingSegments = set()
matchingCells = set()
for cell in activeCells:
synapses = self.connections.synapsesForPresynapticCell(cell)
for synapseData in synapses.values():
segment = synapseData.segment
permanence = synapseData.permanence
if permanence >= self.connectedPermanence:
numActiveConnectedSynapsesForSegment[segment] += 1
if (numActiveConnectedSynapsesForSegment[segment] >=
self.activationThreshold):
activeSegments.add(segment)
predictiveCells.add(self.connections.cellForSegment(segment))
if permanence > 0 and self.predictedSegmentDecrement > 0:
numActiveSynapsesForSegment[segment] += 1
if numActiveSynapsesForSegment[segment] >= self.minThreshold:
matchingSegments.add(segment)
matchingCells.add(self.connections.cellForSegment(segment))
return activeSegments, predictiveCells, matchingSegments, matchingCells
# ==============================
# Helper functions
# ==============================
def bestMatchingCell(self, cells, activeCells):
"""
Gets the cell with the best matching segment
(see `TM.bestMatchingSegment`) that has the largest number of active
synapses of all best matching segments.
If none were found, pick the least used cell (see `TM.leastUsedCell`).
@param cells (set) Indices of cells
@param activeCells (set) Indices of active cells
@return (tuple) Contains:
`cell` (int),
`bestSegment` (int)
"""
maxSynapses = 0
bestCell = None
bestSegment = None
for cell in cells:
segment, numActiveSynapses = self.bestMatchingSegment(cell, activeCells)
if segment is not None and numActiveSynapses > maxSynapses:
maxSynapses = numActiveSynapses
bestCell = cell
bestSegment = segment
if bestCell is None:
bestCell = self.leastUsedCell(cells)
return bestCell, bestSegment
def bestMatchingSegment(self, cell, activeCells):
"""
Gets the segment on a cell with the largest number of activate synapses,
including all synapses with non-zero permanences.
@param cell (int) Cell index
@param activeCells (set) Indices of active cells
@return (tuple) Contains:
`segment` (int),
`connectedActiveSynapses` (set)
"""
maxSynapses = self.minThreshold
bestSegment = None
bestNumActiveSynapses = None
for segment in self.connections.segmentsForCell(cell):
numActiveSynapses = 0
for synapse in self.connections.synapsesForSegment(segment):
synapseData = self.connections.dataForSynapse(synapse)
if ( (synapseData.presynapticCell in activeCells) and
synapseData.permanence > 0):
numActiveSynapses += 1
if numActiveSynapses >= maxSynapses:
maxSynapses = numActiveSynapses
bestSegment = segment
bestNumActiveSynapses = numActiveSynapses
return bestSegment, bestNumActiveSynapses
def leastUsedCell(self, cells):
"""
Gets the cell with the smallest number of segments.
Break ties randomly.
@param cells (set) Indices of cells
@return (int) Cell index
"""
leastUsedCells = set()
minNumSegments = float("inf")
for cell in cells:
numSegments = len(self.connections.segmentsForCell(cell))
if numSegments < minNumSegments:
minNumSegments = numSegments
leastUsedCells = set()
if numSegments == minNumSegments:
leastUsedCells.add(cell)
i = self._random.getUInt32(len(leastUsedCells))
return sorted(leastUsedCells)[i]
def activeSynapsesForSegment(self, segment, activeCells):
"""
Returns the synapses on a segment that are active due to lateral input
from active cells.
@param segment (int) Segment index
@param activeCells (set) Indices of active cells
@return (set) Indices of active synapses on segment
"""
synapses = set()
for synapse in self.connections.synapsesForSegment(segment):
synapseData = self.connections.dataForSynapse(synapse)
if synapseData.presynapticCell in activeCells:
synapses.add(synapse)
return synapses
def adaptSegment(self, segment, activeSynapses,
permanenceIncrement, permanenceDecrement):
"""
Updates synapses on segment.
Strengthens active synapses; weakens inactive synapses.
@param segment (int) Segment index
@param activeSynapses (set) Indices of active synapses
@param permanenceIncrement (float) Amount to increment active synapses
@param permanenceDecrement (float) Amount to decrement inactive synapses
"""
# Need to copy synapses for segment set below because it will be modified
# during iteration by `destroySynapse`
for synapse in set(self.connections.synapsesForSegment(segment)):
synapseData = self.connections.dataForSynapse(synapse)
permanence = synapseData.permanence
if synapse in activeSynapses:
permanence += permanenceIncrement
else:
permanence -= permanenceDecrement
# Keep permanence within min/max bounds
permanence = max(0.0, min(1.0, permanence))
if (abs(permanence) < EPSILON):
self.connections.destroySynapse(synapse)
else:
self.connections.updateSynapsePermanence(synapse, permanence)
def pickCellsToLearnOn(self, n, segment, winnerCells):
"""
Pick cells to form distal connections to.
TODO: Respect topology and learningRadius
@param n (int) Number of cells to pick
@param segment (int) Segment index
@param winnerCells (set) Indices of winner cells in `t`
@return (set) Indices of cells picked
"""
candidates = set(winnerCells)
# Remove cells that are already synapsed on by this segment
for synapse in self.connections.synapsesForSegment(segment):
synapseData = self.connections.dataForSynapse(synapse)
presynapticCell = synapseData.presynapticCell
if presynapticCell in candidates:
candidates.remove(presynapticCell)
n = min(n, len(candidates))
candidates = sorted(candidates)
cells = set()
# Pick n cells randomly
for _ in range(n):
i = self._random.getUInt32(len(candidates))
cells.add(candidates[i])
del candidates[i]
return cells
def columnForCell(self, cell):
"""
Returns the index of the column that a cell belongs to.
@param cell (int) Cell index
@return (int) Column index
"""
self._validateCell(cell)
return int(cell / self.cellsPerColumn)
def cellsForColumn(self, column):
"""
Returns the indices of cells that belong to a column.
@param column (int) Column index
@return (set) Cell indices
"""
self._validateColumn(column)
start = self.cellsPerColumn * self.getCellIndex(column)
end = start + self.cellsPerColumn
return set(xrange(start, end))
def numberOfColumns(self):
"""
Returns the number of columns in this layer.
@return (int) Number of columns
"""
return reduce(mul, self.columnDimensions, 1)
def numberOfCells(self):
"""
Returns the number of cells in this layer.
@return (int) Number of cells
"""
return self.numberOfColumns() * self.cellsPerColumn
def mapCellsToColumns(self, cells):
"""
Maps cells to the columns they belong to
@param cells (set) Cells
@return (dict) Mapping from columns to their cells in `cells`
"""
cellsForColumns = defaultdict(set)
for cell in cells:
column = self.columnForCell(cell)
cellsForColumns[column].add(cell)
return cellsForColumns
def write(self, proto):
"""
Writes serialized data to proto object
@param proto (DynamicStructBuilder) Proto object
"""
proto.columnDimensions = self.columnDimensions
proto.cellsPerColumn = self.cellsPerColumn
proto.activationThreshold = self.activationThreshold
proto.initialPermanence = self.initialPermanence
proto.connectedPermanence = self.connectedPermanence
proto.minThreshold = self.minThreshold
proto.maxNewSynapseCount = self.maxNewSynapseCount
proto.permanenceIncrement = self.permanenceIncrement
proto.permanenceDecrement = self.permanenceDecrement
proto.predictedSegmentDecrement = self.predictedSegmentDecrement
self.connections.write(proto.connections)
self._random.write(proto.random)
proto.activeCells = list(self.activeCells)
proto.predictiveCells = list(self.predictiveCells)
proto.activeSegments = list(self.activeSegments)
proto.winnerCells = list(self.winnerCells)
proto.matchingSegments = list(self.matchingSegments)
proto.matchingCells = list(self.matchingCells)
@classmethod
def read(cls, proto):
"""
Reads deserialized data from proto object
@param proto (DynamicStructBuilder) Proto object
@return (TemporalMemory) TemporalMemory instance
"""
tm = object.__new__(cls)
tm.columnDimensions = list(proto.columnDimensions)
tm.cellsPerColumn = int(proto.cellsPerColumn)
tm.activationThreshold = int(proto.activationThreshold)
tm.initialPermanence = proto.initialPermanence
tm.connectedPermanence = proto.connectedPermanence
tm.minThreshold = int(proto.minThreshold)
tm.maxNewSynapseCount = int(proto.maxNewSynapseCount)
tm.permanenceIncrement = proto.permanenceIncrement
tm.permanenceDecrement = proto.permanenceDecrement
tm.predictedSegmentDecrement = proto.predictedSegmentDecrement
tm.connections = Connections.read(proto.connections)
tm._random = Random()
tm._random.read(proto.random)
tm.activeCells = set([int(x) for x in proto.activeCells])
tm.predictiveCells = set([int(x) for x in proto.predictiveCells])
tm.activeSegments = set([int(x) for x in proto.activeSegments])
tm.winnerCells = set([int(x) for x in proto.winnerCells])
tm.matchingSegments = set([int(x) for x in proto.matchingSegments])
tm.matchingCells = set([int(x) for x in proto.matchingCells])
return tm
def __eq__(self, other):
"""
Equality operator for TemporalMemory instances.
Checks if two instances are functionally identical
(might have different internal state).
@param other (TemporalMemory) TemporalMemory instance to compare to
"""
if self.columnDimensions != other.columnDimensions: return False
if self.cellsPerColumn != other.cellsPerColumn: return False
if self.activationThreshold != other.activationThreshold: return False
if abs(self.initialPermanence - other.initialPermanence) > EPSILON:
return False
if abs(self.connectedPermanence - other.connectedPermanence) > EPSILON:
return False
if self.minThreshold != other.minThreshold: return False
if self.maxNewSynapseCount != other.maxNewSynapseCount: return False
if abs(self.permanenceIncrement - other.permanenceIncrement) > EPSILON:
return False
if abs(self.permanenceDecrement - other.permanenceDecrement) > EPSILON:
return False
if abs(self.predictedSegmentDecrement - other.predictedSegmentDecrement) > EPSILON:
return False
if self.connections != other.connections: return False
if self.activeCells != other.activeCells: return False
if self.predictiveCells != other.predictiveCells: return False
if self.winnerCells != other.winnerCells: return False
if self.matchingSegments != other.matchingSegments: return False
if self.matchingCells != other.matchingCells: return False
return True
def __ne__(self, other):
"""
Non-equality operator for TemporalMemory instances.
Checks if two instances are not functionally identical
(might have different internal state).
@param other (TemporalMemory) TemporalMemory instance to compare to
"""
return not self.__eq__(other)
def _validateColumn(self, column):
"""
Raises an error if column index is invalid.
@param column (int) Column index
"""
if column >= self.numberOfColumns() or column < 0:
raise IndexError("Invalid column")
def _validateCell(self, cell):
"""
Raises an error if cell index is invalid.
@param cell (int) Cell index
"""
if cell >= self.numberOfCells() or cell < 0:
raise IndexError("Invalid cell")
@classmethod
def getCellIndices(cls, cells):
return [cls.getCellIndex(c) for c in cells]
@staticmethod
def getCellIndex(cell):
return cell