def evaluate_goodness_of_fit(ann, target_patterns):
sum_g = 0.
assert isinstance(ann, NeocorticalNetwork)
# recall
for pattern in target_patterns:
_, output = ann.get_IO(pattern[0])
sum_g += Tools.get_pattern_correlation(pattern[1], output)
return sum_g / float(len(target_patterns)) # returns the goodness of fit
def evaluate_ann_with_bipolar_output(ann, set_size):
print "Evaluating the ANN-object.."
sum_corr = 0.
corr_ctr = 0.
neocortically_recalled_pairs = []
for [target_in, target_out] in training_patterns_associative[:5*set_size]:
obtained_in, obtained_out = ann.get_IO(target_in)
sum_corr += Tools.get_pattern_correlation(target_out, Tools.get_bipolar_in_out_values(obtained_out))
corr_ctr += 1
neocortically_recalled_pairs.append([obtained_in, obtained_out])
g = sum_corr / corr_ctr
goodness_str = "goodness of fit, g=" + "{:6.4f}".format(g)
print goodness_str
