RachelPerceptronPython: Difference between revisions
Jump to navigation
Jump to search
(New page: <pre> #!/usr/bin/python down = False up = True def dp (inputs, weights) : sum = 0.0 i = 0 while(i < len(inputs)) : sum += inputs[i]*weights[i] i += 1 return sum learnin...) |
No edit summary |
||
Line 6: | Line 6: | ||
def dp (inputs, weights) : | def dp (inputs, weights) : | ||
sum | return sum(i*w for i,w in zip(inputs, weights)) | ||
learning_rate = 0.1 | learning_rate = 0.1 | ||
Line 23: | Line 17: | ||
prod = dp( inputs, weights ) | prod = dp( inputs, weights ) | ||
print "dot_product: " + str(prod) | print "dot_product: " + str(prod) | ||
if | if prod > threshhold : | ||
return 1 | return 1 | ||
else : | else : | ||
Line 31: | Line 25: | ||
def bump_weights( inputs, up_or_down ) : | def bump_weights( inputs, up_or_down ) : | ||
print "bump_weights" | print "bump_weights" | ||
x | for x, val in enumerate( inputs ) : | ||
val = inputs[x] | val = inputs[x] | ||
if | if val == 1 : | ||
if | if up_or_down : | ||
weights[x] += learning_rate | weights[x] += learning_rate | ||
else : | else : | ||
weights[x] -= learning_rate | weights[x] -= learning_rate | ||
Line 69: | Line 61: | ||
bump_weights( inputs, up ) | bump_weights( inputs, up ) | ||
count += 1 | count += 1 | ||
if | if count == len(datasets) and correct != [True,True,True,True]: | ||
count = 0 | count = 0 | ||
print "\n" | print "\n" | ||
</pre> | </pre> |
Latest revision as of 12:21, 5 March 2010
#!/usr/bin/python down = False up = True def dp (inputs, weights) : return sum(i*w for i,w in zip(inputs, weights)) learning_rate = 0.1 threshhold = 0.5 weights = [0,0,0] def co(inputs) : print "co" prod = dp( inputs, weights ) print "dot_product: " + str(prod) if prod > threshhold : return 1 else : return 0 # iterate over inputs and bump the corresponding weights if the input was 1 def bump_weights( inputs, up_or_down ) : print "bump_weights" for x, val in enumerate( inputs ) : val = inputs[x] if val == 1 : if up_or_down : weights[x] += learning_rate else : weights[x] -= learning_rate datasets = [[1,0,0,1],[1,0,1,1],[1,1,0,1],[1,1,1,0]] #learn([1,1,0],1) #print weights # weights remains a global variable count = 0 correct = [False,False,False,False] while count < len(datasets) : dataset = datasets[count] inputs = dataset[0:3] expected = dataset[3] print "inputs: " + ', '.join(str(x) for x in inputs ) print "weights: " + ', '.join(str(x) for x in weights ) result = co( inputs ) print "expected: " + str(expected) print "and got : " + str(result) correct[count] = True if result > expected : print "too big" correct[count] = False bump_weights( inputs, down ) if result < expected : print "too small" correct[count] = False bump_weights( inputs, up ) count += 1 if count == len(datasets) and correct != [True,True,True,True]: count = 0 print "\n"