0.7, 100.0, 0.1, turnover_rate, # gamma, epsilon, nu, turnover rate
0.10, 0.95, 0.8, 2.0, weighting_dg, # k_m, k_r, a_i, alpha. alpha is 2 in 4.1
_ASYNC_FLAG=_ASYNC_FLAG, _TURNOVER_MODE=_TURNOVER_MODE)
# ============ Config. X: ============
for i in range(1):
for train_set_size_ctr in range(2, 3):
hpc.reset_hpc_module()
tar_patts = []
for p in training_patterns_associative[:5*train_set_size_ctr]:
tar_patts.append(p[1])
ann = NeocorticalNetwork(io_dim, 30, io_dim, 0.01, 0.9)
print "Starting experiment; HPC chaotic recall i iterations and HPC pseudopatterns..."
# This also saves the experiment results:
# relative frequency as in successful 2x5 goodness of fit.
Experiments_4_x.experiment_4_2_hpc_recall_every_i_iters(
hpc, train_set_size_ctr, training_patterns_associative[:5 * train_set_size_ctr], train_iters=15)
# For now, this is the ONLY place where the counter is incremented.
Tools.increment_experiment_counter()
print "Performing memory consolidation.."
# This is rather hard-coded for demo-purposes.
NeocorticalMemoryConsolidation.iterate_over_experiments_suite_span_output_demo_local(Tools.get_experiment_counter()-1,
Tools.get_experiment_counter())
print "Please see the saved_data/ folder for the associated experiment output."
Tools.increment_experiment_counter()
hpc._ASYNC_FLAG = False
# ============ Config. X: ============
for i in range(20):
for train_set_size_ctr in range(2, 6):
hpc.reset_hpc_module()
tar_patts = []
for p in training_patterns_heterogeneous[:5*train_set_size_ctr]:
tar_patts.append(p[1])
print "Starting experiment 4.1, HPC chaotic recall i iters and HPC pseudopatterns..."
# This also saves the experiment results:
# relative frequency as in successful 2x5 goodness of fit.
Experiments_4_x.experiment_4_2_hpc_recall_every_i_iters(
hpc, train_set_size_ctr, training_patterns_heterogeneous[:5 * train_set_size_ctr], train_iters=15)
# For now, this is the ONLY place where the counter is incremented.
Tools.increment_experiment_counter()
hpc._turnover_rate = 0.50
# ============ Config. X: ============
for i in range(20):
for train_set_size_ctr in range(2, 6):
hpc.reset_hpc_module()
tar_patts = []
for p in training_patterns_heterogeneous[:5*train_set_size_ctr]:
tar_patts.append(p[1])
print "Starting experiment 4.1, HPC chaotic recall i iters and HPC pseudopatterns..."
