def _addRegion(self, src_name, dest_name, params):
sensor = src_name
sp_name = "sp_" + dest_name
tp_name = "tp_" + dest_name
class_name = "class_" + dest_name
try:
self.network.regions[sp_name]
self.network.regions[tp_name]
self.network.regions[class_name]
self.network.link(sensor, sp_name, "UniformLink", "")
except Exception as e:
# sp
self.network.addRegion(sp_name, "py.SPRegion", json.dumps(params['SP_PARAMS']))
self.network.link(sensor, sp_name, "UniformLink", "")
# tp
self.network.addRegion(tp_name, "py.TPRegion", json.dumps(params['TP_PARAMS']))
self.network.link(sp_name, tp_name, "UniformLink", "")
# class
self.network.addRegion( class_name, "py.CLAClassifierRegion", json.dumps(params['CLASSIFIER_PARAMS']))
self.network.link(tp_name, class_name, "UniformLink", "")
encoder = MultiEncoder()
encoder.addMultipleEncoders(params['CLASSIFIER_ENCODE_PARAMS'])
self.classifier_encoder_list[class_name] = encoder
self.classifier_input_list[class_name] = tp_name
def createEncoder():
"""
Creates and returns a #MultiEncoder including a ScalarEncoder for
energy consumption and a DateEncoder for the time of the day.
@see nupic/encoders/__init__.py for type to file-name mapping
@see nupic/encoders for encoder source files
"""
encoder = MultiEncoder()
encoder.addMultipleEncoders({
"consumption": {
"fieldname": u"consumption",
"type": "ScalarEncoder",
"name": u"consumption",
"minval": 0.0,
"maxval": 100.0,
"clipInput": True,
"w": 21,
"n": 500
},
"timestamp_timeOfDay": {
"fieldname": u"timestamp",
"type": "DateEncoder",
"name": u"timestamp_timeOfDay",
"timeOfDay": (21, 9.5)
}
})
return encoder
def _createNetwork():
"""Create network with one RecordSensor region."""
network = Network()
network.addRegion('sensor', 'py.RecordSensor', '{}')
sensorRegion = network.regions['sensor'].getSelf()
# Add an encoder.
encoderParams = {
'consumption': {
'fieldname': 'consumption',
'resolution': 0.88,
'seed': 1,
'name': 'consumption',
'type': 'RandomDistributedScalarEncoder'
}
}
encoder = MultiEncoder()
encoder.addMultipleEncoders(encoderParams)
sensorRegion.encoder = encoder
# Add a data source.
testDir = os.path.dirname(os.path.abspath(__file__))
inputFile = os.path.join(testDir, 'fixtures', 'gymdata-test.csv')
dataSource = FileRecordStream(streamID=inputFile)
sensorRegion.dataSource = dataSource
# Get and set what field index we want to predict.
predictedIdx = dataSource.getFieldNames().index('consumption')
network.regions['sensor'].setParameter('predictedFieldIdx', predictedIdx)
return network
def createEncoder(newEncoders):
"""
Creates and returns a MultiEncoder.
@param newEncoders (dict) Keys are the encoders' names, values are
dicts of the params; an example is shown below.
@return encoder (MultiEncoder) See nupic.encoders.multi.py.
Example input:
{"energy": {"fieldname": u"energy",
"type": "ScalarEncoder",
"name": u"consumption",
"minval": 0.0,
"maxval": 100.0,
"w": 21,
"n": 500},
"timestamp": {"fieldname": u"timestamp",
"type": "DateEncoder",
"name": u"timestamp_timeOfDay",
"timeOfDay": (21, 9.5)},
}
"""
encoder = MultiEncoder()
encoder.addMultipleEncoders(newEncoders)
return encoder
def _createEncoder():
"""Create the encoder instance for our test and return it."""
encoder = MultiEncoder()
encoder.addMultipleEncoders(
{
"timestamp": dict(fieldname="timestamp", type="DateEncoder", timeOfDay=(5, 5)),
"attendeeCount": dict(
fieldname="attendeeCount",
type="ScalarEncoder",
name="attendeeCount",
minval=0,
maxval=270,
clipInput=True,
w=5,
resolution=10,
),
"consumption": dict(
fieldname="consumption",
type="ScalarEncoder",
name="consumption",
minval=0,
maxval=115,
clipInput=True,
w=5,
resolution=5,
),
}
)
return encoder
def _createNetwork():
"""Create a network with a RecordSensor region and a SDRClassifier region"""
network = Network()
network.addRegion('sensor', 'py.RecordSensor', '{}')
network.addRegion('classifier', 'py.SDRClassifierRegion', '{}')
_createSensorToClassifierLinks(network, 'sensor', 'classifier')
# Add encoder to sensor region.
sensorRegion = network.regions['sensor'].getSelf()
encoderParams = {'consumption': {'fieldname': 'consumption',
'resolution': 0.88,
'seed': 1,
'name': 'consumption',
'type': 'RandomDistributedScalarEncoder'}}
encoder = MultiEncoder()
encoder.addMultipleEncoders(encoderParams)
sensorRegion.encoder = encoder
# Add data source.
testDir = os.path.dirname(os.path.abspath(__file__))
inputFile = os.path.join(testDir, 'fixtures', 'gymdata-test.csv')
dataSource = FileRecordStream(streamID=inputFile)
sensorRegion.dataSource = dataSource
# Get and set what field index we want to predict.
predictedIdx = dataSource.getFieldNames().index('consumption')
network.regions['sensor'].setParameter('predictedFieldIdx', predictedIdx)
return network
def createEncoder(newEncoders):
"""
Creates and returns a MultiEncoder.
@param newEncoders (dict) Keys are the encoders' names, values are
dicts of the params; an example is shown below.
@return encoder (MultiEncoder) See nupic.encoders.multi.py.
Example input:
{"energy": {"fieldname": u"energy",
"type": "ScalarEncoder",
"name": u"consumption",
"minval": 0.0,
"maxval": 100.0,
"w": 21,
"n": 500},
"timestamp": {"fieldname": u"timestamp",
"type": "DateEncoder",
"name": u"timestamp_timeOfDay",
"timeOfDay": (21, 9.5)},
}
"""
encoder = MultiEncoder()
encoder.addMultipleEncoders(newEncoders)
return encoder
def _createNetwork():
"""Create network with one RecordSensor region."""
network = Network()
network.addRegion('sensor', 'py.RecordSensor', '{}')
sensorRegion = network.regions['sensor'].getSelf()
# Add an encoder.
encoderParams = {'consumption': {'fieldname': 'consumption',
'resolution': 0.88,
'seed': 1,
'name': 'consumption',
'type': 'RandomDistributedScalarEncoder'}}
encoder = MultiEncoder()
encoder.addMultipleEncoders(encoderParams)
sensorRegion.encoder = encoder
# Add a data source.
testDir = os.path.dirname(os.path.abspath(__file__))
inputFile = os.path.join(testDir, 'fixtures', 'gymdata-test.csv')
dataSource = FileRecordStream(streamID=inputFile)
sensorRegion.dataSource = dataSource
# Get and set what field index we want to predict.
network.regions['sensor'].setParameter('predictedField', 'consumption')
return network
def _createNetwork():
"""Create a network with a RecordSensor region and a SDRClassifier region"""
network = Network()
network.addRegion('sensor', 'py.RecordSensor', '{}')
network.addRegion('classifier', 'py.SDRClassifierRegion', '{}')
_createSensorToClassifierLinks(network, 'sensor', 'classifier')
# Add encoder to sensor region.
sensorRegion = network.regions['sensor'].getSelf()
encoderParams = {
'consumption': {
'fieldname': 'consumption',
'resolution': 0.88,
'seed': 1,
'name': 'consumption',
'type': 'RandomDistributedScalarEncoder'
}
}
encoder = MultiEncoder()
encoder.addMultipleEncoders(encoderParams)
sensorRegion.encoder = encoder
# Add data source.
testDir = os.path.dirname(os.path.abspath(__file__))
inputFile = os.path.join(testDir, 'fixtures', 'gymdata-test.csv')
dataSource = FileRecordStream(streamID=inputFile)
sensorRegion.dataSource = dataSource
# Get and set what field index we want to predict.
network.regions['sensor'].setParameter('predictedField', 'consumption')
return network
def _createEncoder(encoders):
"""
Creates and returns a MultiEncoder.
@param encoders: (dict) Keys are the encoders' names, values are dicts of
the params; an example is shown below.
@return encoder: (MultiEncoder) See nupic.encoders.multi.py. Example input:
{"energy": {"fieldname": u"energy",
"type": "ScalarEncoder",
"name": u"consumption",
"minval": 0.0,
"maxval": 100.0,
"w": 21,
"n": 500},
"timestamp": {"fieldname": u"timestamp",
"type": "DateEncoder",
"name": u"timestamp_timeOfDay",
"timeOfDay": (21, 9.5)},
}
"""
if not isinstance(encoders, dict):
raise TypeError("Encoders specified in incorrect format.")
encoder = MultiEncoder()
encoder.addMultipleEncoders(encoders)
return encoder
def _createEncoder(encoders):
"""
Creates and returns a MultiEncoder.
@param encoders: (dict) Keys are the encoders' names, values are dicts of
the params; an example is shown below.
@return encoder: (MultiEncoder) See nupic.encoders.multi.py. Example input:
{"energy": {"fieldname": u"energy",
"type": "ScalarEncoder",
"name": u"consumption",
"minval": 0.0,
"maxval": 100.0,
"w": 21,
"n": 500},
"timestamp": {"fieldname": u"timestamp",
"type": "DateEncoder",
"name": u"timestamp_timeOfDay",
"timeOfDay": (21, 9.5)},
}
"""
if not isinstance(encoders, dict):
raise TypeError("Encoders specified in incorrect format.")
encoder = MultiEncoder()
encoder.addMultipleEncoders(encoders)
return encoder
def _createEncoder():
"""Create the encoder instance for our test and return it."""
encoder = MultiEncoder()
encoder.addMultipleEncoders({
'timestamp':
dict(fieldname='timestamp',
type='DateEncoder',
timeOfDay=(5, 5),
forced=True),
'attendeeCount':
dict(fieldname='attendeeCount',
type='ScalarEncoder',
name='attendeeCount',
minval=0,
maxval=270,
clipInput=True,
w=5,
resolution=10,
forced=True),
'consumption':
dict(fieldname='consumption',
type='ScalarEncoder',
name='consumption',
minval=0,
maxval=115,
clipInput=True,
w=5,
resolution=5,
forced=True),
})
return encoder
def createEncoder(encoderParams):
'''
Create a multi-encoder from params.
'''
encoder = MultiEncoder()
encoder.addMultipleEncoders(encoderParams)
return encoder
def createSensors(network, sensors):
for sensor in sensors:
dataSource = FileRecordStream(streamID=sensor["source"])
dataSource.setAutoRewind(True)
encoder = MultiEncoder()
encoder.addMultipleEncoders(fieldEncodings=sensor["encodings"])
s = createRegion(network, sensor)
s = s.getSelf()
s.dataSource = dataSource
s.encoder = encoder
return network
def createCategoryEncoder():
encoder = MultiEncoder()
encoder.addMultipleEncoders({
"gym": {
"type": "CategoryEncoder",
"fieldname": u"gym",
"name": u"gym",
"categoryList": ['Hornsby', 'Melbourne', 'Epping', 'Chadstone', 'North', 'Bondi', 'Pitt', 'Park', 'Canberra', 'Darlinghurst'],
"w": 21,
},
})
return encoder
def createClassifierEncoder():
"""Create the encoder instance for our test and return it."""
encoder = MultiEncoder()
encoder.addMultipleEncoders({
"y": {
"type": "CategoryEncoder",
"categoryList": ['label_1', 'label_2'],
"fieldname": u"y",
"name": u"y",
"w": 21,
},
})
return encoder
def createClassifierEncoder():
"""Create the encoder instance for our test and return it."""
encoder = MultiEncoder()
encoder.addMultipleEncoders({
"y": {
"type": "CategoryEncoder",
"categoryList": ['label_1', 'label_2'],
"fieldname": u"y",
"name": u"y",
"w": 21,
},
})
return encoder
def _createEncoder():
"""Create the encoder instance for our test and return it."""
encoder = MultiEncoder()
encoder.addMultipleEncoders({
'timestamp': dict(fieldname='timestamp', type='DateEncoder',
timeOfDay=(5,5), forced=True),
'attendeeCount': dict(fieldname='attendeeCount', type='ScalarEncoder',
name='attendeeCount', minval=0, maxval=270,
clipInput=True, w=5, resolution=10, forced=True),
'consumption': dict(fieldname='consumption',type='ScalarEncoder',
name='consumption', minval=0,maxval=115,
clipInput=True, w=5, resolution=5, forced=True),
})
return encoder
def createSensorEncoder():
"""Create the encoder instance for our test and return it."""
encoder = MultiEncoder()
encoder.addMultipleEncoders({
"x": {
"type": "ScalarEncoder",
"fieldname": u"x",
"name": u"x",
"maxval": 100.0,
"minval": 0.0,
"n": 100,
"w": 21,
"clipInput": True,
},
})
return encoder
def createSensorEncoder():
"""Create the encoder instance for our test and return it."""
encoder = MultiEncoder()
encoder.addMultipleEncoders({
"x": {
"type": "ScalarEncoder",
"fieldname": u"x",
"name": u"x",
"maxval": 100.0,
"minval": 0.0,
"n": 100,
"w": 21,
"clipInput": True,
},
})
return encoder
def _makeRegion(self, name, params):
sp_name = "sp_" + name
if self.tp_enable:
tp_name = "tp_" + name
class_name = "class_" + name
# addRegion
self.network.addRegion(sp_name, "py.SPRegion", json.dumps(params['SP_PARAMS']))
if self.tp_enable:
self.network.addRegion(tp_name, "py.TPRegion", json.dumps(params['TP_PARAMS']))
self.network.addRegion( class_name, "py.CLAClassifierRegion", json.dumps(params['CLASSIFIER_PARAMS']))
encoder = MultiEncoder()
encoder.addMultipleEncoders(self.class_encoder_params)
self.classifier_encoder_list[class_name] = encoder
if self.tp_enable:
self.classifier_input_list[class_name] = tp_name
else:
self.classifier_input_list[class_name] = sp_name
def _makeRegion(self, name, params):
sp_name = "sp_" + name
if self.tp_enable:
tp_name = "tp_" + name
class_name = "class_" + name
# addRegion
self.network.addRegion(sp_name, "py.SPRegion", json.dumps(params['SP_PARAMS']))
if self.tp_enable:
self.network.addRegion(tp_name, "py.TPRegion", json.dumps(params['TP_PARAMS']))
self.network.addRegion( class_name, "py.CLAClassifierRegion", json.dumps(params['CLASSIFIER_PARAMS']))
encoder = MultiEncoder()
encoder.addMultipleEncoders(self.class_encoder_params)
self.classifier_encoder_list[class_name] = encoder
if self.tp_enable:
self.classifier_input_list[class_name] = tp_name
else:
self.classifier_input_list[class_name] = sp_name
def createEncoder(multilevelAnomaly=False):
encoder = MultiEncoder()
if multilevelAnomaly == False:
encoder.addMultipleEncoders({
"cpu": {
"fieldname": u"cpu",
"type": "ScalarEncoder",
"name": u"cpu",
"minval": 0.0,
"maxval": 100.0,
"clipInput": True,
"w": 21,
"n": 500
}
})
else:
encoder.addMultipleEncoders({
"cpu": {
"fieldname": u"cpu",
"type": "ScalarEncoder",
"name": u"cpu",
"minval": 0.0,
"maxval": 100.0,
"clipInput": True,
"w": 21,
"n": 500
},
"mem": {
"fieldname": u"mem",
"type": "ScalarEncoder",
"name": u"mem",
"minval": 0.0,
"maxval": 100.0,
"clipInput": True,
"w": 21,
"n": 500
}
})
return encoder
def createEncoder():
# TODO: vector
encoder = MultiEncoder()
encoder.addMultipleEncoders({
"consumption": {
"clipInput": True,
"type": "ScalarEncoder",
"fieldname": u"consumption",
"name": u"consumption",
"maxval": 100.0,
"minval": 0.0,
"n": 50,
"w": 21,
},
"timestamp_timeOfDay": {
"fieldname": u"timestamp",
"name": u"timestamp_timeOfDay",
"timeOfDay": (21, 9.5),
"type": "DateEncoder",
},
})
return encoder
def createEncoder():
"""Create the encoder instance for our test and return it."""
encoder = MultiEncoder()
encoder.addMultipleEncoders({
"consumption": {
"clipInput": True,
"fieldname": u"consumption",
"maxval": 100.0,
"minval": 0.0,
"n": 50,
"name": u"consumption",
"type": "ScalarEncoder",
"w": 21,
},
"timestamp_timeOfDay": {
"fieldname": u"timestamp",
"name": u"timestamp_timeOfDay",
"timeOfDay": (21, 9.5),
"type": "DateEncoder",
},
})
return encoder
def createEncoder():
"""Create the encoder instance for our test and return it."""
encoder = MultiEncoder()
encoder.addMultipleEncoders({
"consumption": {
"clipInput": True,
"fieldname": u"consumption",
"maxval": 100.0,
"minval": 0.0,
"n": 50,
"name": u"consumption",
"type": "ScalarEncoder",
"w": 21,
},
"timestamp_timeOfDay": {
"fieldname": u"timestamp",
"name": u"timestamp_timeOfDay",
"timeOfDay": (21, 9.5),
"type": "DateEncoder",
},
})
return encoder
def createEncoder():
"""
Creates and returns a #MultiEncoder including a ScalarEncoder for
energy consumption and a DateEncoder for the time of the day.
@see nupic/encoders/__init__.py for type to file-name mapping
@see nupic/encoders for encoder source files
"""
encoder = MultiEncoder()
encoder.addMultipleEncoders({
"consumption": {"fieldname": u"consumption",
"type": "ScalarEncoder",
"name": u"consumption",
"minval": 0.0,
"maxval": 100.0,
"clipInput": True,
"w": 21,
"n": 500},
"timestamp_timeOfDay": {"fieldname": u"timestamp",
"type": "DateEncoder",
"name": u"timestamp_timeOfDay",
"timeOfDay": (21, 9.5)}
})
return encoder
def _createNetwork(self):
def deepupdate(original, update):
"""
Recursively update a dict.
Subdict's won't be overwritten but also updated.
"""
if update is None:
return None
for key, value in original.iteritems():
if not key in update:
update[key] = value
elif isinstance(value, dict):
deepupdate(value, update[key])
return update
self.network = Network()
# check
# if self.selectivity not in self.dest_region_params.keys():
# raise Exception, "There is no selected region : " + self.selectivity
if not len(self.net_structure.keys()) == len(set(self.net_structure.keys())):
raise Exception, "There is deplicated net_structure keys : " + self.net_structure.keys()
# sensor
for sensor_name, params in self.sensor_params.items():
self.network.addRegion(sensor_name, "py.RecordSensor", json.dumps({"verbosity": 0}))
sensor = self.network.regions[sensor_name].getSelf()
# set encoder
#params = deepupdate(cn.SENSOR_PARAMS, params)
encoder = MultiEncoder()
encoder.addMultipleEncoders( params )
sensor.encoder = encoder
sensor.dataSource = DataBuffer()
# network
print 'create element ...'
for name in self.dest_region_params.keys():
change_params = self.dest_region_params[name]
params = deepupdate(self.default_params, change_params)
# input width
input_width = 0
for source in [s for s,d in self.net_structure.items() if name in d]:
if source in self.sensor_params.keys():
sensor = self.network.regions[source].getSelf()
input_width += sensor.encoder.getWidth()
else:
input_width += params['TP_PARAMS']['cellsPerColumn'] * params['TP_PARAMS']['columnCount']
params['SP_PARAMS']['inputWidth'] = input_width
self._makeRegion(name, params)
# link
print 'link network ...'
for source, dest_list in self.net_structure.items():
for dest in dest_list:
if source in self.sensor_params.keys():
self._linkRegion(source, dest)
else:
if self.tp_enable:
self._linkRegion("tp_" + source, dest)
else:
self._linkRegion("sp_" + source, dest)
# initialize
print 'initializing network ...'
self.network.initialize()
for name in self.dest_region_params.keys():
self._initRegion(name)
return
def _createNetwork(self):
def deepupdate(original, update):
"""
Recursively update a dict.
Subdict's won't be overwritten but also updated.
"""
for key, value in original.iteritems():
if not key in update:
update[key] = value
elif isinstance(value, dict):
deepupdate(value, update[key])
return update
from nupic.algorithms.anomaly import computeAnomalyScore
from nupic.encoders import MultiEncoder
from nupic.engine import Network
import create_network as cn
import json
import itertools
self.network = Network()
# sensor
for sensor_name, change_params in self.sensor_params.items():
self.network.addRegion(sensor_name, "py.RecordSensor", json.dumps({"verbosity": 0}))
sensor = self.network.regions[sensor_name].getSelf()
# set encoder
params = deepupdate(cn.SENSOR_PARAMS, change_params)
encoder = MultiEncoder()
encoder.addMultipleEncoders( params )
sensor.encoder = encoder
# set datasource
sensor.dataSource = cn.DataBuffer()
# network
print 'create network ...'
for source, dest_list in self.net_structure.items():
for dest in dest_list:
change_params = self.dest_resgion_data[dest]
params = deepupdate(cn.PARAMS, change_params)
if source in self.sensor_params.keys():
sensor = self.network.regions[source].getSelf()
params['SP_PARAMS']['inputWidth'] = sensor.encoder.getWidth()
self._addRegion(source, dest, params)
else:
self._addRegion("tp_" + source, dest, params)
# initialize
print 'initializing network ...'
self.network.initialize()
for name in set( itertools.chain.from_iterable( self.net_structure.values() )):
self._initRegion(name)
# TODO: 1-3-1構造で, TPのセル数をむやみに増やすことは逆効果になるのでは?
return
def createEncoder(encoderParams): encoder = MultiEncoder() encoder.addMultipleEncoders(encoderParams) return encoder
def createEncoder(encoderParams):
encoder = MultiEncoder()
encoder.addMultipleEncoders(encoderParams)
return encoder
def _createNetwork(self):
def deepupdate(original, update):
"""
Recursively update a dict.
Subdict's won't be overwritten but also updated.
"""
if update is None:
return None
for key, value in original.iteritems():
if not key in update:
update[key] = value
elif isinstance(value, dict):
deepupdate(value, update[key])
return update
self.network = Network()
# check
# if self.selectivity not in self.dest_region_params.keys():
# raise Exception, "There is no selected region : " + self.selectivity
if not len(self.net_structure.keys()) == len(
set(self.net_structure.keys())):
raise Exception, "There is deplicated net_structure keys : " + self.net_structure.keys(
)
# sensor
for sensor_name, params in self.sensor_params.items():
self.network.addRegion(sensor_name, "py.RecordSensor",
json.dumps({"verbosity": 0}))
sensor = self.network.regions[sensor_name].getSelf()
# set encoder
#params = deepupdate(cn.SENSOR_PARAMS, params)
encoder = MultiEncoder()
encoder.addMultipleEncoders(params)
sensor.encoder = encoder
sensor.dataSource = DataBuffer()
# network
print 'create element ...'
for name in self.dest_region_params.keys():
change_params = self.dest_region_params[name]
params = deepupdate(self.default_params, change_params)
# input width
input_width = 0
for source in [
s for s, d in self.net_structure.items() if name in d
]:
if source in self.sensor_params.keys():
sensor = self.network.regions[source].getSelf()
input_width += sensor.encoder.getWidth()
else:
input_width += params['TP_PARAMS'][
'cellsPerColumn'] * params['TP_PARAMS']['columnCount']
params['SP_PARAMS']['inputWidth'] = input_width
self._makeRegion(name, params)
# link
print 'link network ...'
for source, dest_list in self.net_structure.items():
for dest in dest_list:
if source in self.sensor_params.keys():
self._linkRegion(source, dest)
else:
if self.tp_enable:
self._linkRegion("tp_" + source, dest)
else:
self._linkRegion("sp_" + source, dest)
# initialize
print 'initializing network ...'
self.network.initialize()
for name in self.dest_region_params.keys():
self._initRegion(name)
return
class Entity():
def __init__(self, columnCount, InputEncoderParams, toL4ConnectorParamsI,
toL4ConnectorParamsII, toL5ConnectorParams,
toD1ConnectorParams, toD2ConnectorParams, L4Params, L5Params,
k, D1Params, D2Params):
self.columnCount = columnCount
self.toL4ConnectorParamsI = toL4ConnectorParamsI
self.toL4ConnectorParamsII = toL4ConnectorParamsII
self.toL5ConnectorParams = toL5ConnectorParams
self.toD1ConnectorParams = toD1ConnectorParams
self.toD2ConnectorParams = toD2ConnectorParams
self.L4Params = L4Params
self.L5Params = L5Params
self.k = k
self.D1Params = D1Params
self.D2Params = D2Params
self.learning = False
#encoder
from nupic.encoders import MultiEncoder
self.InputEncoder = MultiEncoder()
self.InputEncoder.addMultipleEncoders(InputEncoderParams)
print "Encoder Online"
#spatialPoolers
from nupic.algorithms.spatial_pooler import SpatialPooler
self.toL4ConnectorI = SpatialPooler(
inputDimensions=(toL4ConnectorParamsI["inputDimensions"], ),
columnDimensions=(columnCount, ),
potentialPct=toL4ConnectorParamsI["potentialPct"],
globalInhibition=toL4ConnectorParamsI["globalInhibition"],
localAreaDensity=toL4ConnectorParamsI["localAreaDensity"],
numActiveColumnsPerInhArea=toL4ConnectorParamsI[
"numActiveColumnsPerInhArea"],
synPermInactiveDec=toL4ConnectorParamsI["synPermInactiveDec"],
synPermActiveInc=toL4ConnectorParamsI["synPermActiveInc"],
synPermConnected=toL4ConnectorParamsI["synPermConnected"],
boostStrength=toL4ConnectorParamsI["boostStrength"],
seed=toL4ConnectorParamsI["seed"],
wrapAround=toL4ConnectorParamsI["wrapAround"]) #this part sucks
self.toL4ConnectorII = SpatialPooler(
inputDimensions=(columnCount * 3, ),
columnDimensions=(columnCount, ),
potentialPct=toL4ConnectorParamsII["potentialPct"],
globalInhibition=toL4ConnectorParamsII["globalInhibition"],
localAreaDensity=toL4ConnectorParamsII["localAreaDensity"],
numActiveColumnsPerInhArea=toL4ConnectorParamsII[
"numActiveColumnsPerInhArea"],
synPermInactiveDec=toL4ConnectorParamsII["synPermInactiveDec"],
synPermActiveInc=toL4ConnectorParamsII["synPermActiveInc"],
synPermConnected=toL4ConnectorParamsII["synPermConnected"],
boostStrength=toL4ConnectorParamsII["boostStrength"],
seed=toL4ConnectorParamsII["seed"],
wrapAround=toL4ConnectorParamsII["wrapAround"])
print "toL4Connector Online"
self.toL5Connector = SpatialPooler(
inputDimensions=(columnCount, ),
columnDimensions=(columnCount, ),
potentialPct=toL5ConnectorParams["potentialPct"],
globalInhibition=toL5ConnectorParams["globalInhibition"],
localAreaDensity=toL5ConnectorParams["localAreaDensity"],
numActiveColumnsPerInhArea=toL5ConnectorParams[
"numActiveColumnsPerInhArea"],
synPermInactiveDec=toL5ConnectorParams["synPermInactiveDec"],
synPermActiveInc=toL5ConnectorParams["synPermActiveInc"],
synPermConnected=toL5ConnectorParams["synPermConnected"],
boostStrength=toL5ConnectorParams["boostStrength"],
seed=toL5ConnectorParams["seed"],
wrapAround=toL5ConnectorParams["wrapAround"])
print "toL5Connector Online"
self.toD1Connector = SpatialPooler(
inputDimensions=(columnCount, ),
columnDimensions=(columnCount, ),
potentialPct=toD1ConnectorParams["potentialPct"],
globalInhibition=toD1ConnectorParams["globalInhibition"],
localAreaDensity=toD1ConnectorParams["localAreaDensity"],
numActiveColumnsPerInhArea=toD1ConnectorParams[
"numActiveColumnsPerInhArea"],
synPermInactiveDec=toD1ConnectorParams["synPermInactiveDec"],
synPermActiveInc=toD1ConnectorParams["synPermActiveInc"],
synPermConnected=toD1ConnectorParams["synPermConnected"],
boostStrength=toD1ConnectorParams["boostStrength"],
seed=toD1ConnectorParams["seed"],
wrapAround=toD1ConnectorParams["wrapAround"])
print "toD1Connector Online"
self.toD2Connector = SpatialPooler(
inputDimensions=(columnCount, ),
columnDimensions=(columnCount, ),
potentialPct=toD2ConnectorParams["potentialPct"],
globalInhibition=toD2ConnectorParams["globalInhibition"],
localAreaDensity=toD2ConnectorParams["localAreaDensity"],
numActiveColumnsPerInhArea=toD2ConnectorParams[
"numActiveColumnsPerInhArea"],
synPermInactiveDec=toD2ConnectorParams["synPermInactiveDec"],
synPermActiveInc=toD2ConnectorParams["synPermActiveInc"],
synPermConnected=toD2ConnectorParams["synPermConnected"],
boostStrength=toD2ConnectorParams["boostStrength"],
seed=toD2ConnectorParams["seed"],
wrapAround=toD2ConnectorParams["wrapAround"])
print "toD2Connector Online"
#HTM Layers
from nupic.algorithms.temporal_memory import TemporalMemory
self.L4ActiveColumns = numpy.zeros(self.columnCount, dtype=int)
self.L4 = TemporalMemory(
columnDimensions=(columnCount, ),
seed=42,
)
print "L4 Online"
self.L5ActiveColumns = numpy.zeros(self.columnCount, dtype=int)
self.L5 = TemporalMemory(
columnDimensions=(columnCount, ),
seed=42,
)
print "L5 Online"
self.D1ActiveColumns = numpy.zeros(self.columnCount, dtype=int)
self.D1 = TemporalMemory(
columnDimensions=(columnCount, ),
seed=42,
initialPermanence=0.21,
connectedPermanence=0.5,
)
print "D1 Online"
self.D2ActiveColumns = numpy.zeros(self.columnCount, dtype=int)
self.D2 = TemporalMemory(
columnDimensions=(columnCount, ),
seed=42,
initialPermanence=0.21,
connectedPermanence=0.5,
)
print "D2 Online"
def encode_input(sine1, sine2, angularSpeed1, angularSpeed2,
efferenceCopy):
return self.InputEncoder.encode({
"sine1": sine1,
"sine2": sine2,
"angularSpeed1": angularSpeed1,
"angularSpeed2": angularSpeed2,
"efferenceCopy": efferenceCopy
})
def reset(self):
self.action = 0
self.L4.reset()
self.L5.reset()
self.D1.reset()
self.D2.reset()
def mimic(self, observation, action):
#mimicking only requires remembering the given obs-act pattern,thus the striatum is neglected in this func
self.learning = True
self.action = action
encodedInput = self.encode_input(observation[0], observation[2],
observation[4], observation[5],
str(action))
self.toL4ConnectorI.compute(encodedInput, self.learning,
self.L4ActiveColumns)
self.L4.compute(self.L4ActiveColumns, learn=self.learning)
L4activeColumnIndices = numpy.nonzero(self.L4ActiveColumns)[0]
L5Temp = numpy.zeros(self.columnCount, dtype=int)
for column in L4activeColumnIndices:
L5Temp[column] = 1
self.toL5Connector.compute(L5Temp, self.learning, self.L5ActiveColumns)
self.L5.compute(self.L5ActiveColumns, learn=self.learning)
L5activeColumnIndices = numpy.nonzero(self.L5ActiveColumns)[0]
#no action generation is needed in this func
def learn(self, env, observation, expectedReaction):
#We humans learn by trial and error,so does an AI agent.For neural networks,they have BP,but HTM does not
#have a clear way to reinforcement learn(Where to feed in rewards?).Here I try to do something new.
self.learning = False #...trial
encodedInput = self.encode_input(observation[0], observation[2],
observation[4], observation[5],
str(self.action))
self.toL4ConnectorI.compute(encodedInput, self.learning,
self.L4ActiveColumns)
L4Temp = numpy.zeros(
self.columnCount * 3, dtype=int
) #ready to receive D1's disinhibition and D2's inhibition
L4activeColumnIndices = numpy.nonzero(self.L4ActiveColumns)[0]
for column in L4activeColumnIndices:
L4Temp[int(column) * 3] = 1
D1ActiveColumnsIndices = numpy.nonzero(self.D1ActiveColumns)[0]
for column in D1ActiveColumnsIndices:
L4Temp[int(column) * 3 + 1] = 1
D2ActiveColumnsIndices = numpy.nonzero(self.D2ActiveColumns)[0]
for i in range(self.columnCount - 1):
L4Temp[i * 3 + 2] = 1
for column in D2ActiveColumnsIndices: #achieve inhibition in this way
L4Temp[i * 3 + 2] = 0
self.toL4ConnectorII.compute(L4Temp, self.learning,
self.L4ActiveColumns)
self.L4.compute(self.L4ActiveColumns, learn=self.learning)
L4activeColumnIndices = numpy.nonzero(self.L4ActiveColumns)[0]
L5Temp = numpy.zeros(self.columnCount, dtype=int)
for column in L4activeColumnIndices:
L5Temp[column] = 1
self.toL5Connector.compute(L5Temp, self.learning, self.L5ActiveColumns)
self.L5.compute(self.L5ActiveColumns, learn=self.learning)
L5activeColumnIndices = numpy.nonzero(self.L5ActiveColumns)[0]
#Action Generation
p = 84 #there are 84 bits in the SDR representing the action fed in the agent,this is the "Efference Copy"
count0 = 0
count1 = 0
count2 = 0
for activeIndice in L5activeColumnIndices:
convertedIndice = (activeIndice + 1) * 1126 / columnCount
if convertedIndice <= 1126 - p / 4 and convertedIndice > 1126 - p / 2:
count2 = count2 + 1
if convertedIndice <= 1126 - p / 2 and convertedIndice > 1126 - 3 * p / 4:
count1 = count1 + 1
if convertedIndice <= 1126 - 3 * p / 4 and convertedIndice > 1126 - p:
count0 = count0 + 1
if count2 == max(count0, count1, count2):
self.action = 2
if count1 == max(count0, count1, count2):
self.action = 1
if count0 == max(count0, count1, count2):
self.action = 0
#...and error
if self.action == expectedReaction:
reward = 0.1
else:
reward = -0.1
self.D1.setConnectedPermanence(self.D1.getConnectedPermanence() *
(self.k**(-reward))) #reward
self.D2.setConnectedPermanence(self.D2.getConnectedPermanence() *
(self.k**reward)) #punishment
#Learn to correct mistakes(remember what's right and whats' wrong)
self.learning = True
DTemp = numpy.zeros(self.columnCount, dtype=int)
for column in L5activeColumnIndices:
DTemp[column] = 1
self.toD1Connector.compute(DTemp, self.learning, self.D1ActiveColumns)
self.toD2Connector.compute(DTemp, self.learning, self.D2ActiveColumns)
self.D1.compute(self.D1ActiveColumns, learn=self.learning)
self.D2.compute(self.D2ActiveColumns, learn=self.learning)
return reward
def react(self, observation):
self.learning = False
encodedInput = self.encode_input(observation[0], observation[2],
observation[4], observation[5],
str(self.action))
self.toL4ConnectorI.compute(encodedInput, self.learning,
self.L4ActiveColumns)
L4Temp = numpy.zeros(self.columnCount * 3, dtype=int)
L4activeColumnIndices = numpy.nonzero(self.L4ActiveColumns)[0]
for column in L4activeColumnIndices:
L4Temp[int(column) * 3] = 1
D1ActiveColumnsIndices = numpy.nonzero(self.D1ActiveColumns)[0]
for column in D1ActiveColumnsIndices:
L4Temp[int(column) * 3 + 1] = 1
D2ActiveColumnsIndices = numpy.nonzero(self.D2ActiveColumns)[0]
for i in range(self.columnCount - 1):
L4Temp[i * 3 + 2] = 1
for column in D2ActiveColumnsIndices:
L4Temp[i * 3 + 2] = 0
self.toL4ConnectorII.compute(L4Temp, self.learning,
self.L4ActiveColumns)
self.L4.compute(self.L4ActiveColumns, learn=self.learning)
L4activeColumnIndices = numpy.nonzero(self.L4ActiveColumns)[0]
L5Temp = numpy.zeros(self.columnCount, dtype=int)
for column in L4activeColumnIndices:
L5Temp[column] = 1
self.toL5Connector.compute(L5Temp, self.learning, self.L5ActiveColumns)
self.L5.compute(self.L5ActiveColumns, learn=self.learning)
L5activeColumnIndices = numpy.nonzero(self.L5ActiveColumns)[0]
p = 84
count0 = 0
count1 = 0
count2 = 0
for activeIndice in L5activeColumnIndices:
convertedIndice = (activeIndice + 1) * 1126 / columnCount
if convertedIndice <= 1126 - p / 4 and convertedIndice > 1126 - p / 2:
count2 = count2 + 1
if convertedIndice <= 1126 - p / 2 and convertedIndice > 1126 - 3 * p / 4:
count1 = count1 + 1
if convertedIndice <= 1126 - 3 * p / 4 and convertedIndice > 1126 - p:
count0 = count0 + 1
if count2 == max(count0, count1, count2):
self.action = 2
if count1 == max(count0, count1, count2):
self.action = 1
if count0 == max(count0, count1, count2):
self.action = 0
return self.action
def createEncoder(encoderParams): """Create a multi-encoder from params.""" encoder = MultiEncoder() encoder.addMultipleEncoders(encoderParams) return encoder
def _createNetwork(self):
def deepupdate(original, update):
"""
Recursively update a dict.
Subdict's won't be overwritten but also updated.
"""
if update is None:
return None
for key, value in original.iteritems():
if not key in update:
update[key] = value
elif isinstance(value, dict):
deepupdate(value, update[key])
return update
self.network = Network()
# check
if self.selectivity not in self.dest_resgion_data.keys():
raise Exception, "There is no selected region : " + self.selectivity
if not len(self.net_structure.keys()) == len(set(self.net_structure.keys())):
raise Exception, "There is deplicated net_structure keys : " + self.net_structure.keys()
# sensor
for sensor_name, change_params in self.sensor_params.items():
self.network.addRegion(sensor_name, "py.RecordSensor", json.dumps({"verbosity": 0}))
sensor = self.network.regions[sensor_name].getSelf()
# set encoder
params = deepupdate(cn.SENSOR_PARAMS, change_params)
encoder = MultiEncoder()
encoder.addMultipleEncoders( params )
sensor.encoder = encoder
# set datasource
sensor.dataSource = cn.DataBuffer()
# network
print 'create network ...'
for source, dest_list in self.net_structure.items():
for dest in dest_list:
change_params = self.dest_resgion_data[dest]
params = deepupdate(cn.PARAMS, change_params)
if source in self.sensor_params.keys():
sensor = self.network.regions[source].getSelf()
params['SP_PARAMS']['inputWidth'] = sensor.encoder.getWidth()
self._addRegion(source, dest, params)
else:
#self._addRegion("sp_" + source, dest, params)
self._addRegion("tp_" + source, dest, params)
# initialize
print 'initializing network ...'
self.network.initialize()
for name in set( itertools.chain.from_iterable( self.net_structure.values() )):
self._initRegion(name)
# TODO: 1-3-1構造で, TPのセル数をむやみに増やすことは逆効果になるのでは?
return
