RNN use mean square error does not converge - tensorflow

Question

I am learning RNN through https://medium.com/#erikhallstrm/hello-world-rnn-83cd7105b767. I change the loss function to mean square error and found it does not converge. The output is stuck at 0.5. Somehow, I feel the mistake is inside
midlosses = [tf.squeeze(logits)-tf.squeeze(labels) for logits, labels in zip(logits_series,labels_series)]
But I don't how. I am not familiar with datatype. This may be a silly question. In case I don't make myself clear, the full code is below:
from __future__ import print_function, division
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
num_epochs = 100
total_series_length = 50000
truncated_backprop_length = 15
state_size = 4
num_classes = 1
echo_step = 3
batch_size = 5
num_batches = total_series_length//batch_size//truncated_backprop_length
def generateData():
x = np.array(np.random.choice(2, total_series_length, p=[0.5, 0.5]))
y = np.roll(x, echo_step)
y[0:echo_step] = 0
x = x.reshape((batch_size, -1)) # The first index changing slowest, subseries as rows
y = y.reshape((batch_size, -1))
return (x, y)
tf.reset_default_graph()
batchX_placeholder = tf.placeholder(tf.float32, [batch_size, truncated_backprop_length])
batchY_placeholder = tf.placeholder(tf.float32, [batch_size, truncated_backprop_length])
init_state = tf.placeholder(tf.float32, [batch_size, state_size])
W = tf.Variable(np.random.rand(state_size+1, state_size), dtype=tf.float32)
b = tf.Variable(np.zeros((1,state_size)), dtype=tf.float32)
W2 = tf.Variable(np.random.rand(state_size, num_classes),dtype=tf.float32)
b2 = tf.Variable(np.zeros((1,num_classes)), dtype=tf.float32)
# Unpack columns
inputs_series = tf.unstack(batchX_placeholder, axis=1)
labels_series = tf.unstack(batchY_placeholder, axis=1)
# Forward pass
current_state = init_state
states_series = []
for current_input in inputs_series:
current_input = tf.reshape(current_input, [batch_size, 1])
input_and_state_concatenated = tf.concat([current_input, current_state],axis=1) # Increasing number of columns
next_state = tf.tanh(tf.matmul(input_and_state_concatenated, W) + b) # Broadcasted addition
states_series.append(next_state)
current_state = next_state
logits_series = [tf.matmul(state, W2) + b2 for state in states_series]
#Loss function HERE
midlosses = [tf.squeeze(logits)-tf.squeeze(labels) for logits, labels in zip(logits_series,labels_series)]
losses = tf.square(midlosses)
total_loss = tf.reduce_mean(losses)
train_step = tf.train.AdagradOptimizer(0.3).minimize(total_loss)
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
loss_list = []
for epoch_idx in range(num_epochs):
x,y = generateData()
_current_state = np.zeros((batch_size, state_size))
print("New data, epoch", epoch_idx)
for batch_idx in range(num_batches):
start_idx = batch_idx * truncated_backprop_length
end_idx = start_idx + truncated_backprop_length
batchX = x[:,start_idx:end_idx]
batchY = y[:,start_idx:end_idx]
_total_loss, _train_step, _current_state,_logits_series,_midlosses = sess.run(
[total_loss, train_step, current_state,logits_series,midlosses],
feed_dict={
batchX_placeholder:batchX,
batchY_placeholder:batchY,
init_state:_current_state
})
loss_list.append(_total_loss)
if batch_idx%100 == 0:
print("Step",batch_idx, "Loss", _total_loss)

Answer 1

Just need to replace
logits_series = [tf.matmul(state, W2) + b2 for state in states_series]
by
logits_series = [tf.squeeze(tf.matmul(state, W2) + b2) for state in states_series] #Broadcasted addition
Problem can solved.