def __init__(self):
grid_size = 16
# HEURISTICS: radius = (1/3)*2^(ENCODING_SIZE)
# where ENCODING_SIZE is bit size of every pattern element (8 bits for us)
radius = 24
# Calculate pattern size based on grid_size and size of a Nibble (4)
pattern_size = pow(grid_size, 2) / 4
# Set neural network data size
RbfNetwork.PATTERN_SIZE = pattern_size
# Set neural network default radius
RbfNetwork.DEFAULT_RADIUS = radius
# Set pattern size in RBF knowledge
RbfKnowledge.PATTERN_SIZE = pattern_size
# If there are no persisten memory related files, create them
if not os.path.isfile("persistent_memory/sight_snb.p"):
self.erase_all_knowledge()
# SNB
self.snb = SensoryNeuralBlock("persistent_memory/sight_snb.p",
"persistent_memory/hearing_snb.p")
# Relational Neural Block
self.rnb = RelNetwork.deserialize("persistent_memory/rnb.p")
# Analytical neuron
self.analytical_n = AnalyticalNeuron()
# Addition by memory network
self.am_net = CulturalNetwork.deserialize("persistent_memory/am_net.p")
# Geometric Neural Block
self.gnb = GeometricNeuralBlock.deserialize("persistent_memory/gnb.p")
# Syllables net
self.syllables_net = CulturalNetwork.deserialize(
"persistent_memory/syllables_net.p")
# Words net
self.words_net = CulturalNetwork.deserialize(
"persistent_memory/words_net.p")
# Sight-Syllables rel network
self.ss_rnb = RelNetwork.deserialize("persistent_memory/ss_rnb.p")
# ################### INTENTIONS MODULES ########################################################################
self.episodic_memory = EpisodicMemoriesBlock.deserialize(
"persistent_memory/episodic_memory.p")
self.decisions_block = DecisionsBlock.deserialize(
"persistent_memory/decisions_block.p")
self.internal_state = InternalState.deserialize(
"persistent_memory/internal_state.p")
self.desired_state = InternalState.deserialize(
"persistent_memory/desired_state.p")
# Internal state "Ports" (Three components real valued vector)
self._internal_state_in = None
# Memory that stores short term bip inputs for making a decision
self._intentions_short_term_memory = []
self._output_memory = None
# ###############################################################################################################
# _bbcc_words
self._learning_words = False
self._learning_syllables = False
self._enable_bbcc = False
# Output "ports" (related to senses)
self.s_knowledge_out = None
self.h_knowledge_out = None
# Input "ports" (senses)
self.s_knowledge_in = None
self.h_knowledge_in = None
self._working_domain = "ADDITION"
self.state = "MISS"
def __init__(self, user, project, frontend_request):
grid_size = 16
# HEURISTICS: radius = (1/3)*2^(ENCODING_SIZE)
# where ENCODING_SIZE is bit size of every pattern element (8 bits for us)
radius = 24
# Calculate pattern size based on grid_size and size of a Nibble (4)
pattern_size = pow(grid_size, 2) / 4
# Set neural network data size
RbfNetwork.PATTERN_SIZE = pattern_size
# Set neural network default radius
RbfNetwork.DEFAULT_RADIUS = radius
# Set pattern size in RBF knowledge
RbfKnowledge.PATTERN_SIZE = pattern_size
# If there are no persisten memory related files, create them
self.user = user
self.hearing_id = -1
if frontend_request == "CREATE":
self.brain = brain(user=self.user, name=project)
self.brain.save()
self.project_id = self.brain.id
self.project_name = project
self.create_kernel()
self.message = 'the brain has been created successfully, the id is ' + str(
self.project_id)
if frontend_request == "LOAD":
self.project_id = project
# SNB
self.snb = SensoryNeuralBlock("snb_s", "snb_h", self.project_id)
#print(self.snb.snb_h.__dict__)
#for i in self.snb.snb_h.neuron_list:
#if i._knowledge!= None:
#print(i._knowledge)
# Relational Neural Block
self.rnb = RelNetwork.deserialize("rnb", self.project_id)
#print(self.rnb.__dict__)
#for i in self.rnb.neuron_list:
#if i._knowledge!= None:
#print(i.__dict__)
#print(i._knowledge.__dict__)
# Addition by memory network
self.am_net = CulturalNetwork.deserialize("am_net",
self.project_id)
#print(self.am_net.__dict__)
#for i in self.am_net.group_list:
#if i._knowledge!= None:
#print(i.__dict__)
# Geometric Neural Block
self.gnb = GeometricNeuralBlock.deserialize("gnb", self.project_id)
#print(self.gnb.__dict__)
#for i in self.gnb._addition_structure.neurons:
#if i._knowledge!= None:
#print(i.__dict__)
# Syllables net
self.syllables_net = CulturalNetwork.deserialize(
"syllables_net", self.project_id)
#print(self.syllables_net.__dict__)
#for i in self.syllables_net.group_list:
#if i._knowledge!= None:
#print(i.__dict__)
# Words net
self.words_net = CulturalNetwork.deserialize(
"words_net", self.project_id)
#print(self.words_net.__dict__)
#for i in self.words_net.group_list:
#if i._knowledge!= None:
#print(i.__dict__)
# Sight-Syllables rel network
self.ss_rnb = RelNetwork.deserialize("ss_rnb", self.project_id)
#print(self.ss_rnb.__dict__)
# for i in self.ss_rnb.neuron_list:
# if i._knowledge!= None:
# print(i._knowledge.__dict__)
#################### INTENTIONS MODULES ########################################################################
self.episodic_memory = EpisodicMemoriesBlock.deserialize(
"episodic_memory", self.project_id)
#print(self.episodic_memory.__dict__)
#for i in self.episodic_memory.group_list:
#print(i.__dict__)
#for k in i.group:
#print(k.__dict__)
# if isinstance(k._knowledge, int):
# asd=int(k._knowledge)
# print(asd)
# else:
# print(k._knowledge.__dict__)
self.decisions_block = DecisionsBlock.deserialize(
"decisions_block", self.project_id)
#print(self.decisions_block.__dict__)
#print(self.decisions_block.conscious_block.decision_prediction_block.predictive_net.__dict__)
self.internal_state = InternalState.deserialize(
"internal_state", self.project_id)
#print('internal',self.internal_state.__dict__)
self.desired_state = InternalState.deserialize(
"desired_state", self.project_id)
#print('desired',self.desired_state.__dict__)
self.message = "BRAIN SUCCESFULLY LOADED"
################################################# NON-deserialize data################
# Analytical neuron
self.analytical_n = AnalyticalNeuron()
#print(self.analytical_n.__dict__)
# Internal state "Ports" (Three components real valued vector)
self._internal_state_in = None
# Memory that stores short term bip inputs for making a decision
self._intentions_short_term_memory = []
self._output_memory = None
# ###############################################################################################################
# _bbcc_words
self._learning_words = False
self._learning_syllables = False
self._enable_bbcc = False
# Output "ports" (related to senses)
self.s_knowledge_out = None
self.h_knowledge_out = None
# Input "ports" (senses)
self.s_knowledge_in = None
self.h_knowledge_in = None
self._working_domain = "ADDITION"
self.state = "MISS"