def __init__(
self,
configs=(), # block configuration
labels=(0, 1), # labels
min_val=-1.0, # ScalarEncoder minimum input value
max_val=1.0, # ScalarEncoder maximum input value
num_i=1024, # ScalarEncoder number of statelets
num_ai=128, # ScalarEncoder number of active statelets
num_s=32, # PatternClassifier number of statelets
num_as=8, # PatternClassifier number of active statelets
pct_pool=0.8, # PatternClassifier pool percentage
pct_conn=0.5, # PatternClassifier initial connection percentage
pct_learn=0.25): # PatternClassifier learn percentage
# seed the random number generator
bb.seed(0)
# build blocks from config descriptions if given
blocks = get_blocks(configs)
self.encoders = blocks["encoders"]
self.pc = blocks["pattern_classifier"]
if len(self.encoders) == 0:
self.encoders.append(ScalarEncoder(min_val, max_val, num_i,
num_ai))
if self.pc == None:
num_l = len(labels)
self.pc = PatternClassifier(labels, num_s, num_as, 20, 2, 1,
pct_pool, pct_conn, pct_learn)
for encoder in self.encoders:
self.pc.input.add_child(encoder.output)
def __init__(
self,
num_spc=10, # number of statelets per column
num_dps=10, # number of coincidence detectors per statelet
num_rpd=12, # number of receptors per coincidence detector
d_thresh=6, # coincidence detector threshold
perm_thr=20, # receptor permanence threshold
perm_inc=2, # receptor permanence increment
perm_dec=1, # receptor permanence decrement
random_state=None): # random state integer
if isinstance(random_state, int):
bb.seed(random_state)
self.obj = bb.SequenceLearner(num_spc, num_dps, num_rpd, d_thresh,
perm_thr, perm_inc, perm_dec)
def __init__(
self,
configs=(), # block configuration
min_val=-1.0, # minumum value
max_val=1.0, # maximum value
num_i=1024, # ScalarEncoder number of statelets
num_ai=128, # ScalarEncoder number of active statelets
num_s=512, # PatternPooler number of statelets
num_as=8, # PatternPooler number of active statelets
num_spc=10, # SequenceLearner number of statelets per column
num_dps=10, # SequenceLearner number of coincidence detectors per statelet
num_rpd=12, # SequenceLearner number of receptors per coincidence detector
d_thresh=6, # SequenceLearner coincidence detector threshold
pct_pool=0.8, # PatternPooler pool percentage
pct_conn=0.5, # PatternPooler initial connection percentage
pct_learn=0.25): # PatternPooler learn percentage
self.min_val = min_val
self.max_val = max_val
# seed the random number generator
bb.seed(0)
# build blocks from config descriptions if given
blocks = get_blocks(configs)
self.encoders = blocks["encoders"]
self.pp = blocks["pattern_pooler"]
self.sl = blocks["sequence_learner"]
if len(self.encoders) == 0:
self.encoders.append(ScalarEncoder(min_val, max_val, num_i,
num_ai))
if self.pp == None:
self.pp = PatternPooler(num_s, num_as, 20, 2, 1, pct_pool,
pct_conn, pct_learn)
if self.sl == None:
self.sl = SequenceLearner(num_spc, num_dps, num_rpd, d_thresh, 1,
1, 0)
for encoder in self.encoders:
self.pp.input.add_child(encoder.output)
self.sl.input.add_child(self.pp.output)
self.initialized = False
def __init__(
self,
num_s=512, # number of statelets
num_as=8, # number of active statelets
perm_thr=20, # receptor permanence threshold
perm_inc=2, # receptor permanence increment
perm_dec=1, # receptor permanence decrement
pct_pool=0.8, # pooling percentage
pct_conn=0.5, # initially connected percentage
pct_learn=0.25, # learn percentage
random_state=None): # random state integer
if isinstance(random_state, int):
bb.seed(random_state)
self.obj = bb.PatternPooler(num_s, num_as, perm_thr, perm_inc,
perm_dec, pct_pool, pct_conn, pct_learn)
# sequence_learning.py
#
# TODO: this is out of data and needs updating!!!
# ==============================================================================
import os
import errno
import math
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import brainblocks.bb_backend as bb
from brainblocks.blocks import SymbolsEncoder, SequenceLearner
from sklearn import preprocessing
# seed for deterministic random generator
bb.seed(0)
# printing boolean arrays neatly
np.set_printoptions(
precision=3,
suppress=True,
threshold=1000000,
linewidth=100,
formatter={'bool': lambda bin_val: 'X' if bin_val else '-'})
def mkdir_p(path):
try:
os.makedirs(path)
except OSError as exc:
if exc.errno == errno.EEXIST and os.path.isdir(path):