def testIssue807():
# The following should silently pass. Previous versions segfaulted.
# See https://github.com/numenta/nupic.core/issues/807 for context
from nupic.bindings.algorithms import TemporalMemory
tm = TemporalMemory()
tm.compute(set(), True)
def testIssue807():
# The following should silently pass. Previous versions segfaulted.
# See https://github.com/numenta/nupic.core/issues/807 for context
from nupic.bindings.algorithms import TemporalMemory
tm = TemporalMemory()
tm.compute(set(), True)
cellsPerColumn=8,
initialPermanence=0.21,
connectedPermanence=0.3,
minThreshold=15,
maxNewSynapseCount=40,
permanenceIncrement=0.1,
permanenceDecrement=0.1,
activationThreshold=15,
predictedSegmentDecrement=0.01,
)
for t in range(75):
rnd = random.randrange(2)
for k in range(4):
if rnd == 0:
tm.compute(set(seq1[k][:].nonzero()[0].tolist()), learn=True)
else:
tm.compute(set(seq2[k][:].nonzero()[0].tolist()), learn=True)
print("")
print("-" * 50)
print(
"We now have a look at the output of the TM when presented with the individual"
)
print(
"characters A, B, C, D, X, and Y. We might observe simultaneous predictions when"
)
print(
"presented with character D (predicting A and X), character Y (predicting A and X),"
)
print("and when presented with character C (predicting D and Y).")
class NumentaTMLowLevelDetector(AnomalyDetector):
"""The 'numentaTM' detector, but not using the CLAModel or network API """
def __init__(self, *args, **kwargs):
super(NumentaTMLowLevelDetector, self).__init__(*args, **kwargs)
self.valueEncoder = None
self.encodedValue = None
self.timestampEncoder = None
self.encodedTimestamp = None
self.sp = None
self.spOutput = None
self.tm = None
self.anomalyLikelihood = None
# Set this to False if you want to get results based on raw scores
# without using AnomalyLikelihood. This will give worse results, but
# useful for checking the efficacy of AnomalyLikelihood. You will need
# to re-optimize the thresholds when running with this setting.
self.useLikelihood = True
def getAdditionalHeaders(self):
"""Returns a list of strings."""
return ["raw_score"]
def initialize(self):
# Initialize the RDSE with a resolution; calculated from the data min and
# max, the resolution is specific to the data stream.
rangePadding = abs(self.inputMax - self.inputMin) * 0.2
minVal = self.inputMin - rangePadding
maxVal = (self.inputMax + rangePadding
if self.inputMin != self.inputMax
else self.inputMin + 1)
numBuckets = 130.0
resolution = max(0.001, (maxVal - minVal) / numBuckets)
self.valueEncoder = RandomDistributedScalarEncoder(resolution, seed=42)
self.encodedValue = np.zeros(self.valueEncoder.getWidth(),
dtype=np.uint32)
# Initialize the timestamp encoder
self.timestampEncoder = DateEncoder(timeOfDay=(21, 9.49, ))
self.encodedTimestamp = np.zeros(self.timestampEncoder.getWidth(),
dtype=np.uint32)
inputWidth = (self.timestampEncoder.getWidth() +
self.valueEncoder.getWidth())
self.sp = SpatialPooler(**{
"globalInhibition": True,
"columnDimensions": [2048],
"inputDimensions": [inputWidth],
"potentialRadius": inputWidth,
"numActiveColumnsPerInhArea": 40,
"seed": 1956,
"potentialPct": 0.8,
"boostStrength": 0.0,
"synPermActiveInc": 0.003,
"synPermConnected": 0.2,
"synPermInactiveDec": 0.0005,
})
self.spOutput = np.zeros(2048, dtype=np.float32)
self.tm = TemporalMemory(**{
"activationThreshold": 20,
"cellsPerColumn": 32,
"columnDimensions": (2048,),
"initialPermanence": 0.24,
"maxSegmentsPerCell": 128,
"maxSynapsesPerSegment": 128,
"minThreshold": 13,
"maxNewSynapseCount": 31,
"permanenceDecrement": 0.008,
"permanenceIncrement": 0.04,
"seed": 1960,
})
if self.useLikelihood:
learningPeriod = math.floor(self.probationaryPeriod / 2.0)
self.anomalyLikelihood = anomaly_likelihood.AnomalyLikelihood(
claLearningPeriod=learningPeriod,
estimationSamples=self.probationaryPeriod - learningPeriod,
reestimationPeriod=100
)
def handleRecord(self, inputData):
"""Returns a tuple (anomalyScore, rawScore)."""
# Encode the input data record
self.valueEncoder.encodeIntoArray(
inputData["value"], self.encodedValue)
self.timestampEncoder.encodeIntoArray(
inputData["timestamp"], self.encodedTimestamp)
# Run the encoded data through the spatial pooler
self.sp.compute(np.concatenate((self.encodedTimestamp,
self.encodedValue,)),
True, self.spOutput)
# At the current state, the set of the region's active columns and the set
# of columns that have previously-predicted cells are used to calculate the
# raw anomaly score.
activeColumns = set(self.spOutput.nonzero()[0].tolist())
prevPredictedColumns = set(self.tm.columnForCell(cell)
for cell in self.tm.getPredictiveCells())
rawScore = (len(activeColumns - prevPredictedColumns) /
float(len(activeColumns)))
self.tm.compute(activeColumns)
if self.useLikelihood:
# Compute the log-likelihood score
anomalyScore = self.anomalyLikelihood.anomalyProbability(
inputData["value"], rawScore, inputData["timestamp"])
logScore = self.anomalyLikelihood.computeLogLikelihood(anomalyScore)
return (logScore, rawScore)
return (rawScore, rawScore)
activationThreshold=15,
maxNewSynapseCount=20)
print
print "Training TM on sequences ... "
numRepeatsBatch = 1
numRptsPerSequence = 1
np.random.seed(10)
for rpt in xrange(numRepeatsBatch):
# randomize the order of training sequences
randomIdx = np.random.permutation(range(numTrain))
for i in range(numTrain):
for _ in xrange(numRptsPerSequence):
for t in range(sequenceLength):
tm.compute(activeColumnsTrain[randomIdx[i]][t], learn=True)
tm.reset()
print "Rpt: {}, {} out of {} done ".format(rpt, i, trainData.shape[0])
# run TM over training data
unionLength = 20
print "Running TM on Training Data with union window {}".format(unionLength)
(activeColTrain,
activeCellsTrain,
activeFreqTrain,
predActiveFreqTrain) = runTMOverDatasetFast(tm, activeColumnsTrain, unionLength)
# construct two distance matrices using training data
distMatColumnTrain = calculateDistanceMat(activeColTrain, activeColTrain)
distMatCellTrain = calculateDistanceMat(activeCellsTrain, activeCellsTrain)
distMatActiveFreqTrain = calculateDistanceMat(activeFreqTrain, activeFreqTrain)
def go():
valueEncoder = RandomDistributedScalarEncoder(resolution=0.88, seed=42)
timestampEncoder = DateEncoder(timeOfDay=(
21,
9.49,
))
inputWidth = timestampEncoder.getWidth() + valueEncoder.getWidth()
sp = SpatialPooler(
**{
"globalInhibition": True,
"columnDimensions": [2048],
"inputDimensions": [inputWidth],
"potentialRadius": inputWidth,
"numActiveColumnsPerInhArea": 40,
"seed": 1956,
"potentialPct": 0.8,
"boostStrength": 0.0,
"synPermActiveInc": 0.003,
"synPermConnected": 0.2,
"synPermInactiveDec": 0.0005,
})
tm = TemporalMemory(
**{
"activationThreshold": 20,
"cellsPerColumn": 32,
"columnDimensions": (2048, ),
"initialPermanence": 0.24,
"maxSegmentsPerCell": 128,
"maxSynapsesPerSegment": 128,
"minThreshold": 13,
"maxNewSynapseCount": 31,
"permanenceDecrement": 0.008,
"permanenceIncrement": 0.04,
"seed": 1961,
})
inputPath = os.path.join(os.path.dirname(__file__),
"data/rec-center-hourly.csv")
inputFile = open(inputPath, "rb")
csvReader = csv.reader(inputFile)
csvReader.next()
csvReader.next()
csvReader.next()
encodedValue = np.zeros(valueEncoder.getWidth(), dtype=np.uint32)
encodedTimestamp = np.zeros(timestampEncoder.getWidth(), dtype=np.uint32)
spOutput = np.zeros(2048, dtype=np.float32)
sanityInstance = sanity.SPTMInstance(sp, tm)
for timestampStr, consumptionStr in csvReader:
sanityInstance.waitForUserContinue()
timestamp = datetime.datetime.strptime(timestampStr, "%m/%d/%y %H:%M")
consumption = float(consumptionStr)
timestampEncoder.encodeIntoArray(timestamp, encodedTimestamp)
valueEncoder.encodeIntoArray(consumption, encodedValue)
sensoryInput = np.concatenate((
encodedTimestamp,
encodedValue,
))
sp.compute(sensoryInput, True, spOutput)
activeColumns = np.flatnonzero(spOutput)
predictedCells = tm.getPredictiveCells()
tm.compute(activeColumns)
activeInputBits = np.flatnonzero(sensoryInput)
displayText = {
"timestamp": timestampStr,
"consumption": consumptionStr
}
sanityInstance.appendTimestep(activeInputBits, activeColumns,
predictedCells, displayText)
def run_tm_noise_experiment(dim = 2048,
cellsPerColumn=1,
num_active = 40,
activationThreshold=16,
initialPermanence=0.8,
connectedPermanence=0.50,
minThreshold=16,
maxNewSynapseCount=20,
permanenceIncrement=0.05,
permanenceDecrement=0.00,
predictedSegmentDecrement=0.000,
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255,
seed=42,
num_samples = 1,
num_trials = 1000,
sequence_length = 20,
training_iters = 1,
automatic_threshold = False,
noise_range = range(0, 100, 5)):
"""
Run an experiment tracking the performance of the temporal memory given
noise. The number of active cells and the dimensions of the TM are
fixed. We track performance by comparing the cells predicted to be
active with the cells actually active in the sequence without noise at
every timestep, and averaging across timesteps. Three metrics are used,
correlation (Pearson's r, by numpy.corrcoef), set similarity (Jaccard
index) and cosine similarity (using scipy.spatial.distance.cosine). The
Jaccard set similarity is the canonical metric used in the paper, but
all three metrics tend to produce very similar results.
Typically, this experiment is run to test the influence of activation
threshold on noise tolerance, with multiple different thresholds tested.
However, this experiment could also be used to examine the influence of
factors such as sparsity and sequence length.
Output is written to tm_noise_{threshold}}.txt, including sample size.
We used three different activation threshold settings, 8, 12 and 16, mirroring
the parameters used in the Poirazi neuron model experiment.
"""
if automatic_threshold:
activationThreshold = min(num_active/2, maxNewSynapseCount/2)
minThreshold = min(num_active/2, maxNewSynapseCount/2)
for noise in noise_range:
print noise
for trial in range(num_trials):
tm = TM(columnDimensions=(dim,),
cellsPerColumn=cellsPerColumn,
activationThreshold=activationThreshold,
initialPermanence=initialPermanence,
connectedPermanence=connectedPermanence,
minThreshold=minThreshold,
maxNewSynapseCount=maxNewSynapseCount,
permanenceIncrement=permanenceIncrement,
permanenceDecrement=permanenceDecrement,
predictedSegmentDecrement=predictedSegmentDecrement,
maxSegmentsPerCell=maxSegmentsPerCell,
maxSynapsesPerSegment=maxSynapsesPerSegment,
)#seed=seed)
datapoints = []
canonical_active_cells = []
for sample in range(num_samples):
data = generate_evenly_distributed_data_sparse(dim = dim, num_active = num_active, num_samples = sequence_length)
datapoints.append(data)
for i in range(training_iters):
for j in range(data.nRows()):
activeColumns = set(data.rowNonZeros(j)[0])
tm.compute(activeColumns, learn = True)
tm.reset()
current_active_cells = []
for j in range(data.nRows()):
activeColumns = set(data.rowNonZeros(j)[0])
tm.compute(activeColumns, learn = True)
current_active_cells.append(tm.getActiveCells())
canonical_active_cells.append(current_active_cells)
tm.reset()
# Now that the TM has been trained, check its performance on each sequence with noise added.
correlations = []
similarities = []
csims = []
for datapoint, active_cells in zip(datapoints, canonical_active_cells):
data = copy.deepcopy(datapoint)
apply_noise(data, noise)
predicted_cells = []
for j in range(data.nRows()):
activeColumns = set(data.rowNonZeros(j)[0])
tm.compute(activeColumns, learn = False)
predicted_cells.append(tm.getPredictiveCells())
similarity = [(0.+len(set(predicted) & set(active)))/len((set(predicted) | set(active))) for predicted, active in zip (predicted_cells[:-1], active_cells[1:])]
dense_predicted_cells = convert_cell_lists_to_dense(2048*32, predicted_cells[:-1])
dense_active_cells = convert_cell_lists_to_dense(2048*32, active_cells[1:])
correlation = [numpy.corrcoef(numpy.asarray([predicted, active]))[0, 1] for predicted, active in zip(dense_predicted_cells, dense_active_cells)]
csim = [1 - cosine(predicted, active) for predicted, active in zip(dense_predicted_cells, dense_active_cells)]
correlation = numpy.nan_to_num(correlation)
csim = numpy.nan_to_num(csim)
correlations.append(numpy.mean(correlation))
similarities.append(numpy.mean(similarity))
csims.append(numpy.mean(csim))
correlation = numpy.mean(correlations)
similarity = numpy.mean(similarities)
csim = numpy.mean(csims)
with open("tm_noise_{}.txt".format(activationThreshold), "a") as f:
f.write(str(noise)+", " + str(correlation) + ", " + str(similarity) + ", " + str(csim) + ", " + str(num_trials) + "\n")
def run_tm_union_experiment(dim = 4000,
cellsPerColumn=1,
num_active = 40,
activationThreshold=5,
initialPermanence=0.8,
connectedPermanence=0.50,
minThreshold=5,
maxNewSynapseCount=20,
permanenceIncrement=0.05,
permanenceDecrement=0.00,
predictedSegmentDecrement=0.000,
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255,
seed=42,
num_branches_range = range(50, 51, 1),
onset_length = 5,
training_iters = 10,
num_trials = 10000,
automatic_threshold = True,
save_results = True):
"""
Run an experiment tracking the performance of the temporal memory given
different input dimensions. The number of active cells is kept fixed, so we
are in effect varying the sparsity of the input. We track performance by
comparing the cells predicted to be active with the cells actually active in
the sequence without noise at every timestep, and averaging across timesteps.
Three metrics are used, correlation (Pearson's r, by numpy.corrcoef),
set similarity (Jaccard index) and cosine similarity (using
scipy.spatial.distance.cosine). The Jaccard set similarity is the
canonical metric used in the paper, but all three tend to produce very similar
results.
Output is written to tm_dim_{num_active}.txt, including sample size.
We tested two different dimension settings, 2000 and 4000.
"""
if automatic_threshold:
activationThreshold = min(num_active/2, maxNewSynapseCount/2)
minThreshold = min(num_active/2, maxNewSynapseCount/2)
for num_branches in num_branches_range:
overlaps = []
surprises = []
csims = []
for trial in range(num_trials):
if (trial + 1) % 100 == 0:
print trial + 1
tm = TM(columnDimensions=(dim,),
cellsPerColumn=cellsPerColumn,
activationThreshold=activationThreshold,
initialPermanence=initialPermanence,
connectedPermanence=connectedPermanence,
minThreshold=minThreshold,
maxNewSynapseCount=maxNewSynapseCount,
permanenceIncrement=permanenceIncrement,
permanenceDecrement=permanenceDecrement,
predictedSegmentDecrement=predictedSegmentDecrement,
maxSegmentsPerCell=maxSegmentsPerCell,
maxSynapsesPerSegment=maxSynapsesPerSegment,
seed=seed)
datapoints = []
canonical_active_cells = []
onset = generate_evenly_distributed_data_sparse(dim = dim, num_active = num_active, num_samples = onset_length)
for branch in range(num_branches):
datapoint = numpy.random.choice(dim, num_active, replace = False)
datapoints.append(datapoint)
for i in range(training_iters):
for j in range(onset.nRows()):
activeColumns = set(onset.rowNonZeros(j)[0])
tm.compute(activeColumns, learn = True)
tm.compute(datapoint, learn=True)
tm.reset()
for j in range(onset.nRows()):
activeColumns = set(onset.rowNonZeros(j)[0])
tm.compute(activeColumns, learn = False)
predicted_cells = tm.getPredictiveCells()
datapoint = numpy.random.choice(dim, num_active, replace = False)
overlap = (1. * len(set(predicted_cells) & set(datapoint)))/len(datapoint)
surprise = len(datapoint) - len(set(predicted_cells) & set(datapoint))
dense_predicted_cells = numpy.zeros((dim*cellsPerColumn,))
for cell in predicted_cells:
dense_predicted_cells[cell] = 1.
dense_active_cells = numpy.zeros((dim*cellsPerColumn,))
for cell in datapoint:
dense_active_cells[cell] = 1.
csim = 1 - cosine(dense_predicted_cells, dense_active_cells)
csim = numpy.nan_to_num(csim)
overlaps.append(overlap)
surprises.append(surprise)
csims.append(csim)
overlap = numpy.mean(overlaps)
surprise = numpy.mean(surprises)
csim = numpy.mean(csims)
print dim, overlap, surprise, csim
if save_results:
with open("tm_union_n{}_a{}_c{}.txt".format(dim, num_active, cellsPerColumn), "a") as f:
f.write(str(num_branches)+", " + str(overlap) + ", " + str(surprise) + ", " + str(csim) + ", " + str(num_trials) + "\n")
def runHotgym(numRecords):
with open(_PARAMS_PATH, "r") as f:
modelParams = yaml.safe_load(f)["modelParams"]
enParams = modelParams["sensorParams"]["encoders"]
spParams = modelParams["spParams"]
tmParams = modelParams["tmParams"]
# timeOfDayEncoder = DateEncoder(
# timeOfDay=enParams["timestamp_timeOfDay"]["timeOfDay"])
# weekendEncoder = DateEncoder(
# weekend=enParams["timestamp_weekend"]["weekend"])
# scalarEncoder = RandomDistributedScalarEncoder(
# enParams["consumption"]["resolution"])
rdseParams = RDSE_Parameters()
rdseParams.size = 100
rdseParams.sparsity = .10
rdseParams.radius = 10
scalarEncoder = RDSE(rdseParams)
# encodingWidth = (timeOfDayEncoder.getWidth()
# + weekendEncoder.getWidth()
# + scalarEncoder.getWidth())
encodingWidth = scalarEncoder.size
sp = SpatialPooler(
inputDimensions=(encodingWidth, ),
columnDimensions=(spParams["columnCount"], ),
potentialPct=spParams["potentialPct"],
potentialRadius=encodingWidth,
globalInhibition=spParams["globalInhibition"],
localAreaDensity=spParams["localAreaDensity"],
numActiveColumnsPerInhArea=spParams["numActiveColumnsPerInhArea"],
synPermInactiveDec=spParams["synPermInactiveDec"],
synPermActiveInc=spParams["synPermActiveInc"],
synPermConnected=spParams["synPermConnected"],
boostStrength=spParams["boostStrength"],
seed=spParams["seed"],
wrapAround=True)
tm = TemporalMemory(
columnDimensions=(tmParams["columnCount"], ),
cellsPerColumn=tmParams["cellsPerColumn"],
activationThreshold=tmParams["activationThreshold"],
initialPermanence=tmParams["initialPerm"],
connectedPermanence=spParams["synPermConnected"],
minThreshold=tmParams["minThreshold"],
maxNewSynapseCount=tmParams["newSynapseCount"],
permanenceIncrement=tmParams["permanenceInc"],
permanenceDecrement=tmParams["permanenceDec"],
predictedSegmentDecrement=0.0,
maxSegmentsPerCell=tmParams["maxSegmentsPerCell"],
maxSynapsesPerSegment=tmParams["maxSynapsesPerSegment"],
seed=tmParams["seed"])
results = []
with open(_INPUT_FILE_PATH, "r") as fin:
reader = csv.reader(fin)
headers = next(reader)
next(reader)
next(reader)
for count, record in enumerate(reader):
if count >= numRecords: break
# Convert data string into Python date object.
dateString = datetime.datetime.strptime(record[0],
"%m/%d/%y %H:%M")
# Convert data value string into float.
consumption = float(record[1])
# To encode, we need to provide zero-filled numpy arrays for the encoders
# to populate.
# timeOfDayBits = numpy.zeros(timeOfDayEncoder.getWidth())
# weekendBits = numpy.zeros(weekendEncoder.getWidth())
# consumptionBits = numpy.zeros(scalarEncoder.size)
consumptionBits = SDR(scalarEncoder.size)
# Now we call the encoders to create bit representations for each value.
# timeOfDayEncoder.encodeIntoArray(dateString, timeOfDayBits)
# weekendEncoder.encodeIntoArray(dateString, weekendBits)
scalarEncoder.encode(consumption, consumptionBits)
# Concatenate all these encodings into one large encoding for Spatial
# Pooling.
# encoding = numpy.concatenate(
# [timeOfDayBits, weekendBits, consumptionBits]
# )
encoding = consumptionBits
# Create an array to represent active columns, all initially zero. This
# will be populated by the compute method below. It must have the same
# dimensions as the Spatial Pooler.
# activeColumns = numpy.zeros(spParams["columnCount"])
activeColumns = SDR(spParams["columnCount"])
encodingIn = numpy.uint32(encoding.dense)
minicolumnsOut = numpy.uint32(activeColumns.dense)
# Execute Spatial Pooling algorithm over input space.
sp.compute(encodingIn, True, minicolumnsOut)
activeColumnIndices = numpy.nonzero(minicolumnsOut)[0]
# Execute Temporal Memory algorithm over active mini-columns.
tm.compute(activeColumnIndices, learn=True)
activeCells = tm.getActiveCells()
print(len(activeCells))
results.append(activeCells)
return results
cellsPerColumn=8,
initialPermanence=0.21,
connectedPermanence=0.3,
minThreshold=15,
maxNewSynapseCount=40,
permanenceIncrement=0.1,
permanenceDecrement=0.1,
activationThreshold=15,
predictedSegmentDecrement=0.01,
)
for t in range(75):
rnd = random.randrange(2)
for k in range(4):
if rnd == 0:
tm.compute(set(seq1[k][:].nonzero()[0].tolist()), learn=True)
else:
tm.compute(set(seq2[k][:].nonzero()[0].tolist()), learn=True)
print ""
print "-"*50
print "We now have a look at the output of the TM when presented with the individual"
print "characters A, B, C, D, X, and Y. We might observe simultaneous predictions when"
print "presented with character D (predicting A and X), character Y (predicting A and X),"
print "and when presented with character C (predicting D and Y)."
print "N.B. Due to the stochasticity of this script, we might not observe simultaneous"
print "predictions in *all* the aforementioned characters."
print "-"*50
print ""
showPredictions()
def run_tm_dim_experiment(test_dims = range(300, 3100, 100),
cellsPerColumn=1,
num_active = 256,
activationThreshold=10,
initialPermanence=0.8,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.05,
permanenceDecrement=0.00,
predictedSegmentDecrement=0.000,
maxSegmentsPerCell=4000,
maxSynapsesPerSegment=255,
seed=42,
num_samples = 1000,
sequence_length = 20,
training_iters = 1,
automatic_threshold = False,
save_results = True):
"""
Run an experiment tracking the performance of the temporal memory given
different input dimensions. The number of active cells is kept fixed, so we
are in effect varying the sparsity of the input. We track performance by
comparing the cells predicted to be active with the cells actually active in
the sequence without noise at every timestep, and averaging across timesteps.
Three metrics are used, correlation (Pearson's r, by numpy.corrcoef),
set similarity (Jaccard index) and cosine similarity (using
scipy.spatial.distance.cosine). The Jaccard set similarity is the
canonical metric used in the paper, but all three tend to produce very similar
results.
Output is written to tm_dim_{num_active}.txt, including sample size.
In our experiments, we used the set similarity metric (third column in output)
along with three different values for num_active, 64, 128 and 256. We used
dimensions from 300 to 2900 in each case, testing every 100. 1000 sequences
of length 20 were passed to the TM in each trial.
"""
if automatic_threshold:
activationThreshold = min(num_active/2, maxNewSynapseCount/2)
minThreshold = min(num_active/2, maxNewSynapseCount/2)
print "Using activation threshold {}".format(activationThreshold)
for dim in test_dims:
tm = TM(columnDimensions=(dim,),
cellsPerColumn=cellsPerColumn,
activationThreshold=activationThreshold,
initialPermanence=initialPermanence,
connectedPermanence=connectedPermanence,
minThreshold=minThreshold,
maxNewSynapseCount=maxNewSynapseCount,
permanenceIncrement=permanenceIncrement,
permanenceDecrement=permanenceDecrement,
predictedSegmentDecrement=predictedSegmentDecrement,
maxSegmentsPerCell=maxSegmentsPerCell,
maxSynapsesPerSegment=maxSynapsesPerSegment,
seed=seed)
tm.setMinThreshold(1000)
datapoints = []
canonical_active_cells = []
for sample in range(num_samples):
if (sample + 1) % 10 == 0:
print sample + 1
data = generate_evenly_distributed_data_sparse(dim = dim, num_active = num_active, num_samples = sequence_length)
datapoints.append(data)
for i in range(training_iters):
for j in range(data.nRows()):
activeColumns = set(data.rowNonZeros(j)[0])
tm.compute(activeColumns, learn = True)
tm.reset()
current_active_cells = []
for j in range(data.nRows()):
activeColumns = set(data.rowNonZeros(j)[0])
tm.compute(activeColumns, learn = True)
current_active_cells.append(tm.getActiveCells())
canonical_active_cells.append(current_active_cells)
tm.reset()
# Now that the TM has been trained, check its performance on each sequence with noise added.
correlations = []
similarities = []
csims = []
for datapoint, active_cells in zip(datapoints, canonical_active_cells):
data = copy.deepcopy(datapoint)
predicted_cells = []
for j in range(data.nRows()):
activeColumns = set(data.rowNonZeros(j)[0])
tm.compute(activeColumns, learn = False)
predicted_cells.append(tm.getPredictiveCells())
tm.reset()
similarity = [(0.+len(set(predicted) & set(active)))/len((set(predicted) | set(active))) for predicted, active in zip (predicted_cells[:-1], active_cells[1:])]
dense_predicted_cells = convert_cell_lists_to_dense(dim*cellsPerColumn, predicted_cells[:-1])
dense_active_cells = convert_cell_lists_to_dense(dim*cellsPerColumn, active_cells[1:])
correlation = [numpy.corrcoef(numpy.asarray([predicted, active]))[0, 1] for predicted, active in zip(dense_predicted_cells, dense_active_cells)]
csim = [1 - cosine(predicted, active) for predicted, active in zip(dense_predicted_cells, dense_active_cells)]
correlation = numpy.nan_to_num(correlation)
csim = numpy.nan_to_num(csim)
correlations.append(numpy.mean(correlation))
similarities.append(numpy.mean(similarity))
csims.append(numpy.mean(csim))
correlation = numpy.mean(correlations)
similarity = numpy.mean(similarities)
csim = numpy.mean(csims)
print dim, correlation, similarity, csim
if save_results:
with open("tm_dim_{}.txt".format(num_active), "a") as f:
f.write(str(dim)+", " + str(correlation) + ", " + str(similarity) + ", " + str(csim) + ", " + str(num_samples) + "\n")
activationThreshold=15,
maxNewSynapseCount=20)
print
print "Training TM on sequences ... "
numRepeatsBatch = 1
numRptsPerSequence = 1
np.random.seed(10)
for rpt in xrange(numRepeatsBatch):
# randomize the order of training sequences
randomIdx = np.random.permutation(range(numTrain))
for i in range(numTrain):
for _ in xrange(numRptsPerSequence):
for t in range(sequenceLength):
tm.compute(activeColumnsTrain[randomIdx[i]][t],
learn=True)
tm.reset()
print "Rpt: {}, {} out of {} done ".format(
rpt, i, trainData.shape[0])
# run TM over training data
unionLength = 20
print "Running TM on Training Data with union window {}".format(
unionLength)
(activeColTrain, activeCellsTrain, activeFreqTrain,
predActiveFreqTrain) = runTMOverDatasetFast(tm, activeColumnsTrain,
unionLength)
# construct two distance matrices using training data
distMatColumnTrain = calculateDistanceMat(activeColTrain,
activeColTrain)
for i, s_id in enumerate(seqs_train):
s = uniqueSequences[s_id]
#s = s[0:-1]
#SP_SDR_train = numpy.zeros((seqLength,200))
SP_SDR_train = numpy.zeros((seqLength, 6))
SP_SDR_train = SP_SDR_train.astype(numpy.uint32)
for j, symbol in enumerate(s):
#print "symbol=", symbol
#print "j=", j
SP_SDR_train[j] = SDR_activity_codes[symbol]
SP_SDR_seqs_train.append(SP_SDR_train)
# now train temporal memory
for j, SDR in enumerate(SP_SDR_train):
tp.compute(SDR, learn=True)
# how do we reset the tp ?
tp.reset()
# Now, check predictions of tp
def printTemoralPredictions(SP_activeCol_seq, symbol_seq):
for i, s in enumerate(SP_activeCol_seq):
tp.compute(s, learn=False)
print "TP Winner cells", tp.getWinnerCells()
print "TP Predictive cells", tp.getPredictiveCells()
tp.reset()
print "\n"
class BaseNetwork(object):
def __init__(self, inputMin=None, inputMax=None, runSanity=False):
self.inputMin = inputMin
self.inputMax = inputMax
self.runSanity = runSanity
self.encoder = None
self.encoderOutput = None
self.sp = None
self.spOutput = None
self.spOutputNZ = None
self.tm = None
self.anomalyScore = None
if runSanity:
self.sanity = None
self.defaultEncoderResolution = 0.0001
self.numColumns = 2048
self.cellsPerColumn = 32
self.predictedActiveCells = None
self.previouslyPredictiveCells = None
def initialize(self):
# Scalar Encoder
resolution = self.getEncoderResolution()
self.encoder = RandomDistributedScalarEncoder(resolution, seed=42)
self.encoderOutput = np.zeros(self.encoder.getWidth(), dtype=np.uint32)
# Spatial Pooler
spInputWidth = self.encoder.getWidth()
self.spParams = {
"globalInhibition": True,
"columnDimensions": [self.numColumns],
"inputDimensions": [spInputWidth],
"potentialRadius": spInputWidth,
"numActiveColumnsPerInhArea": 40,
"seed": 1956,
"potentialPct": 0.8,
"boostStrength": 0.0,
"synPermActiveInc": 0.003,
"synPermConnected": 0.2,
"synPermInactiveDec": 0.0005,
}
self.sp = SpatialPooler(**self.spParams)
self.spOutput = np.zeros(self.numColumns, dtype=np.uint32)
# Temporal Memory
self.tmParams = {
"activationThreshold": 20,
"cellsPerColumn": self.cellsPerColumn,
"columnDimensions": (self.numColumns,),
"initialPermanence": 0.24,
"maxSegmentsPerCell": 128,
"maxSynapsesPerSegment": 128,
"minThreshold": 13,
"maxNewSynapseCount": 31,
"permanenceDecrement": 0.008,
"permanenceIncrement": 0.04,
"seed": 1960,
}
self.tm = TemporalMemory(**self.tmParams)
# Sanity
if self.runSanity:
self.sanity = sanity.SPTMInstance(self.sp, self.tm)
def handleRecord(self, scalarValue, label=None, skipEncoding=False,
learningMode=True):
"""Process one record."""
if self.runSanity:
self.sanity.waitForUserContinue()
# Encode the input data record if it hasn't already been encoded.
if not skipEncoding:
self.encodeValue(scalarValue)
# Run the encoded data through the spatial pooler
self.sp.compute(self.encoderOutput, learningMode, self.spOutput)
self.spOutputNZ = self.spOutput.nonzero()[0]
# WARNING: this needs to happen here, before the TM runs.
self.previouslyPredictiveCells = self.tm.getPredictiveCells()
# Run SP output through temporal memory
self.tm.compute(self.spOutputNZ)
self.predictedActiveCells = _computePredictedActiveCells(
self.tm.getActiveCells(), self.previouslyPredictiveCells)
# Anomaly score
self.anomalyScore = _computeAnomalyScore(self.spOutputNZ,
self.previouslyPredictiveCells,
self.cellsPerColumn)
# Run Sanity
if self.runSanity:
self.sanity.appendTimestep(self.getEncoderOutputNZ(),
self.getSpOutputNZ(),
self.previouslyPredictiveCells,
{
'value': scalarValue,
'label':label
})
def encodeValue(self, scalarValue):
self.encoder.encodeIntoArray(scalarValue, self.encoderOutput)
def getEncoderResolution(self):
"""
Compute the Random Distributed Scalar Encoder (RDSE) resolution. It's
calculated from the data min and max, specific to the data stream.
"""
if self.inputMin is None or self.inputMax is None:
return self.defaultEncoderResolution
else:
rangePadding = abs(self.inputMax - self.inputMin) * 0.2
minVal = self.inputMin - rangePadding
maxVal = (self.inputMax + rangePadding
if self.inputMin != self.inputMax
else self.inputMin + 1)
numBuckets = 130.0
return max(self.defaultEncoderResolution, (maxVal - minVal) / numBuckets)
def getEncoderOutputNZ(self):
return self.encoderOutput.nonzero()[0]
def getSpOutputNZ(self):
return self.spOutputNZ
def getTmPredictiveCellsNZ(self):
return self.tm.getPredictiveCells()
def getTmActiveCellsNZ(self):
return self.tm.getActiveCells()
def getTmPredictedActiveCellsNZ(self):
return self.predictedActiveCells
def getRawAnomalyScore(self):
return self.anomalyScore
def run_tm_noise_experiment(dim=2048,
cellsPerColumn=1,
num_active=40,
activationThreshold=16,
initialPermanence=0.8,
connectedPermanence=0.50,
minThreshold=16,
maxNewSynapseCount=20,
permanenceIncrement=0.05,
permanenceDecrement=0.00,
predictedSegmentDecrement=0.000,
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255,
seed=42,
num_samples=1,
num_trials=1000,
sequence_length=20,
training_iters=1,
automatic_threshold=False,
noise_range=range(0, 100, 5)):
"""
Run an experiment tracking the performance of the temporal memory given
noise. The number of active cells and the dimensions of the TM are
fixed. We track performance by comparing the cells predicted to be
active with the cells actually active in the sequence without noise at
every timestep, and averaging across timesteps. Three metrics are used,
correlation (Pearson's r, by numpy.corrcoef), set similarity (Jaccard
index) and cosine similarity (using scipy.spatial.distance.cosine). The
Jaccard set similarity is the canonical metric used in the paper, but
all three metrics tend to produce very similar results.
Typically, this experiment is run to test the influence of activation
threshold on noise tolerance, with multiple different thresholds tested.
However, this experiment could also be used to examine the influence of
factors such as sparsity and sequence length.
Output is written to tm_noise_{threshold}}.txt, including sample size.
We used three different activation threshold settings, 8, 12 and 16, mirroring
the parameters used in the Poirazi neuron model experiment.
"""
if automatic_threshold:
activationThreshold = min(num_active / 2, maxNewSynapseCount / 2)
minThreshold = min(num_active / 2, maxNewSynapseCount / 2)
for noise in noise_range:
print noise
for trial in range(num_trials):
tm = TM(
columnDimensions=(dim, ),
cellsPerColumn=cellsPerColumn,
activationThreshold=activationThreshold,
initialPermanence=initialPermanence,
connectedPermanence=connectedPermanence,
minThreshold=minThreshold,
maxNewSynapseCount=maxNewSynapseCount,
permanenceIncrement=permanenceIncrement,
permanenceDecrement=permanenceDecrement,
predictedSegmentDecrement=predictedSegmentDecrement,
maxSegmentsPerCell=maxSegmentsPerCell,
maxSynapsesPerSegment=maxSynapsesPerSegment,
) #seed=seed)
datapoints = []
canonical_active_cells = []
for sample in range(num_samples):
data = generate_evenly_distributed_data_sparse(
dim=dim,
num_active=num_active,
num_samples=sequence_length)
datapoints.append(data)
for i in range(training_iters):
for j in range(data.nRows()):
activeColumns = set(data.rowNonZeros(j)[0])
tm.compute(activeColumns, learn=True)
tm.reset()
current_active_cells = []
for j in range(data.nRows()):
activeColumns = set(data.rowNonZeros(j)[0])
tm.compute(activeColumns, learn=True)
current_active_cells.append(tm.getActiveCells())
canonical_active_cells.append(current_active_cells)
tm.reset()
# Now that the TM has been trained, check its performance on each sequence with noise added.
correlations = []
similarities = []
csims = []
for datapoint, active_cells in zip(datapoints,
canonical_active_cells):
data = copy.deepcopy(datapoint)
apply_noise(data, noise)
predicted_cells = []
for j in range(data.nRows()):
activeColumns = set(data.rowNonZeros(j)[0])
tm.compute(activeColumns, learn=False)
predicted_cells.append(tm.getPredictiveCells())
similarity = [(0. + len(set(predicted) & set(active))) / len(
(set(predicted) | set(active)))
for predicted, active in zip(
predicted_cells[:-1], active_cells[1:])]
dense_predicted_cells = convert_cell_lists_to_dense(
2048 * 32, predicted_cells[:-1])
dense_active_cells = convert_cell_lists_to_dense(
2048 * 32, active_cells[1:])
correlation = [
numpy.corrcoef(numpy.asarray([predicted, active]))[0, 1]
for predicted, active in zip(dense_predicted_cells,
dense_active_cells)
]
csim = [
1 - cosine(predicted, active) for predicted, active in zip(
dense_predicted_cells, dense_active_cells)
]
correlation = numpy.nan_to_num(correlation)
csim = numpy.nan_to_num(csim)
correlations.append(numpy.mean(correlation))
similarities.append(numpy.mean(similarity))
csims.append(numpy.mean(csim))
correlation = numpy.mean(correlations)
similarity = numpy.mean(similarities)
csim = numpy.mean(csims)
with open("tm_noise_{}.txt".format(activationThreshold), "a") as f:
f.write(
str(noise) + ", " + str(correlation) + ", " + str(similarity) +
", " + str(csim) + ", " + str(num_trials) + "\n")
class BaseNetwork(object):
def __init__(self, inputMin=None, inputMax=None, runSanity=False):
self.inputMin = inputMin
self.inputMax = inputMax
self.runSanity = runSanity
self.encoder = None
self.encoderOutput = None
self.sp = None
self.spOutput = None
self.spOutputNZ = None
self.tm = None
self.anomalyScore = None
if runSanity:
self.sanity = None
self.defaultEncoderResolution = 0.0001
self.numColumns = 2048
self.cellsPerColumn = 32
self.predictedActiveCells = None
self.previouslyPredictiveCells = None
def initialize(self):
# Scalar Encoder
resolution = self.getEncoderResolution()
self.encoder = RandomDistributedScalarEncoder(resolution, seed=42)
self.encoderOutput = np.zeros(self.encoder.getWidth(), dtype=np.uint32)
# Spatial Pooler
spInputWidth = self.encoder.getWidth()
self.spParams = {
"globalInhibition": True,
"columnDimensions": [self.numColumns],
"inputDimensions": [spInputWidth],
"potentialRadius": spInputWidth,
"numActiveColumnsPerInhArea": 40,
"seed": 1956,
"potentialPct": 0.8,
"boostStrength": 5.0,
"synPermActiveInc": 0.003,
"synPermConnected": 0.2,
"synPermInactiveDec": 0.0005,
}
self.sp = SpatialPooler(**self.spParams)
self.spOutput = np.zeros(self.numColumns, dtype=np.uint32)
# Temporal Memory
self.tmParams = {
"activationThreshold": 20,
"cellsPerColumn": self.cellsPerColumn,
"columnDimensions": (self.numColumns,),
"initialPermanence": 0.24,
"maxSegmentsPerCell": 128,
"maxSynapsesPerSegment": 128,
"minThreshold": 13,
"maxNewSynapseCount": 31,
"permanenceDecrement": 0.008,
"permanenceIncrement": 0.04,
"seed": 1960,
}
self.tm = TemporalMemory(**self.tmParams)
# Sanity
if self.runSanity:
self.sanity = sanity.SPTMInstance(self.sp, self.tm)
def handleRecord(self, scalarValue, label=None, skipEncoding=False,
learningMode=True):
"""Process one record."""
if self.runSanity:
self.sanity.waitForUserContinue()
# Encode the input data record if it hasn't already been encoded.
if not skipEncoding:
self.encodeValue(scalarValue)
# Run the encoded data through the spatial pooler
self.sp.compute(self.encoderOutput, learningMode, self.spOutput)
self.spOutputNZ = self.spOutput.nonzero()[0]
# WARNING: this needs to happen here, before the TM runs.
self.previouslyPredictiveCells = self.tm.getPredictiveCells()
# Run SP output through temporal memory
self.tm.compute(self.spOutputNZ)
self.predictedActiveCells = _computePredictedActiveCells(
self.tm.getActiveCells(), self.previouslyPredictiveCells)
# Anomaly score
self.anomalyScore = _computeAnomalyScore(self.spOutputNZ,
self.previouslyPredictiveCells,
self.cellsPerColumn)
# Run Sanity
if self.runSanity:
self.sanity.appendTimestep(self.getEncoderOutputNZ(),
self.getSpOutputNZ(),
self.previouslyPredictiveCells,
{
'value': scalarValue,
'label':label
})
def encodeValue(self, scalarValue):
self.encoder.encodeIntoArray(scalarValue, self.encoderOutput)
def getEncoderResolution(self):
"""
Compute the Random Distributed Scalar Encoder (RDSE) resolution. It's
calculated from the data min and max, specific to the data stream.
"""
if self.inputMin is None or self.inputMax is None:
return self.defaultEncoderResolution
else:
rangePadding = abs(self.inputMax - self.inputMin) * 0.2
minVal = self.inputMin - rangePadding
maxVal = (self.inputMax + rangePadding
if self.inputMin != self.inputMax
else self.inputMin + 1)
numBuckets = 130.0
return max(self.defaultEncoderResolution, (maxVal - minVal) / numBuckets)
def getEncoderOutputNZ(self):
return self.encoderOutput.nonzero()[0]
def getSpOutputNZ(self):
return self.spOutputNZ
def getTmPredictiveCellsNZ(self):
return self.tm.getPredictiveCells()
def getTmActiveCellsNZ(self):
return self.tm.getActiveCells()
def getTmPredictedActiveCellsNZ(self):
return self.predictedActiveCells
def getRawAnomalyScore(self):
return self.anomalyScore
def run_tm_dim_experiment(test_dims = range(300, 3100, 100),
cellsPerColumn=1,
num_active = 256,
activationThreshold=10,
initialPermanence=0.8,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.05,
permanenceDecrement=0.00,
predictedSegmentDecrement=0.000,
maxSegmentsPerCell=4000,
maxSynapsesPerSegment=255,
seed=42,
num_samples = 1000,
sequence_length = 20,
training_iters = 1,
automatic_threshold = False,
save_results = True):
"""
Run an experiment tracking the performance of the temporal memory given
different input dimensions. The number of active cells is kept fixed, so we
are in effect varying the sparsity of the input. We track performance by
comparing the cells predicted to be active with the cells actually active in
the sequence without noise at every timestep, and averaging across timesteps.
Three metrics are used, correlation (Pearson's r, by numpy.corrcoef),
set similarity (Jaccard index) and cosine similarity (using
scipy.spatial.distance.cosine). The Jaccard set similarity is the
canonical metric used in the paper, but all three tend to produce very similar
results.
Output is written to tm_dim_{num_active}.txt, including sample size.
In our experiments, we used the set similarity metric (third column in output)
along with three different values for num_active, 64, 128 and 256. We used
dimensions from 300 to 2900 in each case, testing every 100. 1000 sequences
of length 20 were passed to the TM in each trial.
"""
if automatic_threshold:
activationThreshold = min(num_active/2, maxNewSynapseCount/2)
minThreshold = min(num_active/2, maxNewSynapseCount/2)
print "Using activation threshold {}".format(activationThreshold)
for dim in test_dims:
tm = TM(columnDimensions=(dim,),
cellsPerColumn=cellsPerColumn,
activationThreshold=activationThreshold,
initialPermanence=initialPermanence,
connectedPermanence=connectedPermanence,
minThreshold=minThreshold,
maxNewSynapseCount=maxNewSynapseCount,
permanenceIncrement=permanenceIncrement,
permanenceDecrement=permanenceDecrement,
predictedSegmentDecrement=predictedSegmentDecrement,
maxSegmentsPerCell=maxSegmentsPerCell,
maxSynapsesPerSegment=maxSynapsesPerSegment,
seed=seed)
tm.setMinThreshold(1000)
datapoints = []
canonical_active_cells = []
for sample in range(num_samples):
if (sample + 1) % 10 == 0:
print sample + 1
data = generate_evenly_distributed_data_sparse(dim = dim, num_active = num_active, num_samples = sequence_length)
datapoints.append(data)
for i in range(training_iters):
for j in range(data.nRows()):
activeColumns = set(data.rowNonZeros(j)[0])
tm.compute(activeColumns, learn = True)
tm.reset()
current_active_cells = []
for j in range(data.nRows()):
activeColumns = set(data.rowNonZeros(j)[0])
tm.compute(activeColumns, learn = True)
current_active_cells.append(tm.getActiveCells())
canonical_active_cells.append(current_active_cells)
tm.reset()
# Now that the TM has been trained, check its performance on each sequence with noise added.
correlations = []
similarities = []
csims = []
for datapoint, active_cells in zip(datapoints, canonical_active_cells):
data = copy.deepcopy(datapoint)
predicted_cells = []
for j in range(data.nRows()):
activeColumns = set(data.rowNonZeros(j)[0])
tm.compute(activeColumns, learn = False)
predicted_cells.append(tm.getPredictiveCells())
tm.reset()
similarity = [(0.+len(set(predicted) & set(active)))/len((set(predicted) | set(active))) for predicted, active in zip (predicted_cells[:-1], active_cells[1:])]
dense_predicted_cells = convert_cell_lists_to_dense(dim*cellsPerColumn, predicted_cells[:-1])
dense_active_cells = convert_cell_lists_to_dense(dim*cellsPerColumn, active_cells[1:])
correlation = [numpy.corrcoef(numpy.asarray([predicted, active]))[0, 1] for predicted, active in zip(dense_predicted_cells, dense_active_cells)]
csim = [1 - cosine(predicted, active) for predicted, active in zip(dense_predicted_cells, dense_active_cells)]
correlation = numpy.nan_to_num(correlation)
csim = numpy.nan_to_num(csim)
correlations.append(numpy.mean(correlation))
similarities.append(numpy.mean(similarity))
csims.append(numpy.mean(csim))
correlation = numpy.mean(correlations)
similarity = numpy.mean(similarities)
csim = numpy.mean(csims)
print dim, correlation, similarity, csim
if save_results:
with open("tm_dim_{}.txt".format(num_active), "a") as f:
f.write(str(dim)+", " + str(correlation) + ", " + str(similarity) + ", " + str(csim) + ", " + str(num_samples) + "\n")