n_in=data_set_x.get_value(borrow=True).shape[1],
n_out=n_hidden)
output = LogisticRegression(input=lstm_1.output,
n_in=n_hidden,
n_out=data_set_x.get_value(borrow=True).shape[1])
################################
# Objective function and GD
################################
print 'defining cost, parameters, and learning function...'
# the cost we minimize during training is the negative log likelihood of
# the model
cost = T.mean(output.cross_entropy_binary(y))
#Defining params
params = lstm_1.params + output.params
# updates from ADAM
updates = Adam(cost, params)
#######################
# Objective function
#######################
print 'compiling train....'
train_model = theano.function(
inputs=[index],
#reconstructed_regressions = T.concatenate([log_reg.reconstructed_x,lin_reg.reconstructed_x],axis=1) # #reverse_layer = LinearRegression(reconstructed_regressions, 2*lstm_2_hidden, lstm_2_hidden,False) lstm_3 = LSTM(rng, log_reg.reconstructed_x, lstm_2_hidden, lstm_1_hidden) lstm_4 = LSTM(rng, lstm_3.output, lstm_1_hidden, 30) init_reg.reconstruct(lstm_4.output) difference = (ahead - init_reg.reconstructed_x)**2 encoder_cost = T.mean(difference) cross_entropy_cost = T.mean(log_reg.cross_entropy_binary(y)) #y_hat_mean = T.mean(log_reg.p_y_given_x,axis=0) # #z_hat_mean = T.mean(lin_reg.E_y_given_x,axis=0) # #z_variance = lin_reg.E_y_given_x - z_hat_mean #z_var = z_variance.reshape((60,2,1)) #must reshape for outer product # #y_variance = log_reg.p_y_given_x - y_hat_mean #y_var = y_variance.reshape((60,1,10)) # #product = T.batched_dot(z_var,y_var) #an outer product across batches # #product_mean_sqr = (T.mean(product,axis=0) **2) #
#reconstructed_regressions = T.concatenate([log_reg.reconstructed_x,lin_reg.reconstructed_x],axis=1) # #reverse_layer = LinearRegression(reconstructed_regressions, 2*lstm_2_hidden, lstm_2_hidden,False) lstm_3 = LSTM(rng,log_reg.reconstructed_x,lstm_2_hidden,lstm_1_hidden) lstm_4 = LSTM(rng,lstm_3.output,lstm_1_hidden,30) init_reg.reconstruct(lstm_4.output) difference = (ahead-init_reg.reconstructed_x) ** 2 encoder_cost = T.mean( difference ) cross_entropy_cost = T.mean(log_reg.cross_entropy_binary(y)) #y_hat_mean = T.mean(log_reg.p_y_given_x,axis=0) # #z_hat_mean = T.mean(lin_reg.E_y_given_x,axis=0) # #z_variance = lin_reg.E_y_given_x - z_hat_mean #z_var = z_variance.reshape((60,2,1)) #must reshape for outer product # #y_variance = log_reg.p_y_given_x - y_hat_mean #y_var = y_variance.reshape((60,1,10)) # #product = T.batched_dot(z_var,y_var) #an outer product across batches # #product_mean_sqr = (T.mean(product,axis=0) **2) #
# Architecture: input --> LSTM --> predict one-ahead
lstm_1 = LSTM(rng, x, n_in=data_set_x.get_value(borrow=True).shape[1], n_out=n_hidden)
output = LogisticRegression(input=lstm_1.output, n_in=n_hidden, n_out=data_set_x.get_value(borrow=True).shape[1])
################################
# Objective function and GD
################################
print 'defining cost, parameters, and learning function...'
# the cost we minimize during training is the negative log likelihood of
# the model
cost = T.mean(output.cross_entropy_binary(y))
#Defining params
params = lstm_1.params + output.params
# updates from ADAM
updates = Adam(cost, params)
#######################
# Objective function
#######################
print 'compiling train....'
train_model = theano.function(inputs=[index], outputs=cost,
updates=updates,
