pr = nn.update_stochastic(X_train[i], Y_train[i, 0], lrate)
LL += pr
LL /= float(X_train.shape[0])
er_val = error_rate(X_val, Y_val, nn)
er_train = error_rate(X_train, Y_train, nn)
er_test = error_rate(X_test, Y_test, nn)
er.append(er_val)
print "error rate on val db: hdim: {}, er rate: {}".format(hdim, er_val)
print "error rate on train db: hdim: {}, er rate: {}".format(hdim, er_train)
print "error rate on test db: hdim: {}, er rate: {}".format(hdim, er_test)
if train == 'batch':
for hdim in hdims:
nn = NeuralNet(X_train.shape[1], hdim, 6, lam)
for it in range(20):
nn.update_batch(X_train, Y_train, lrate)
er_val = error_rate(X_val, Y_val, nn)
er.append(er_val)
print "error rate on val db: hdim: {}, er rate: {}".format(hdim, er_val)
pl.plot(hdims, er, 'g^-')
pl.title('Model Selection on Neural Network, MNIST')
pl.xlabel('Hidden Layer Units')
pl.ylabel('Error Rate on Validate Dataset')
pl.ylim([0.0, 0.1])
pl.show()
