theano_example.py

import theano
import theano.tensor as T

# Batch size = 32, Input Dimension = 500, Hidden Dimension = 50, Number of Classes = 5

# Define symbolic variables
x = T.matrix('x')
y = T.vector('y', dtype='int64')
w1 = T.matrix('w1')
w2 = T.matrix('w2')

# Forward pass: compute scores
a = x.dot(w1)
a_relu = T.nnet.relu(a)
scores = a_relu.dot(w2)

# Forward pass: compute softmax loss
probs = T.nnet.softmax(scores)
loss = T.nnet.categorical_crossentropy(probs, y).mean()

# Backward pass: compute gradients
dw1, dw2 = T.grad(loss, [w1, w2])

# Compile function
f = theano.function(
  inputs = [x, y, w1, w2],
  outputs = [loss, scores, dw1, dw2],
)

# Run the function
xx = np.random.rand(32, 500)
yy = np.random.randint(5, size=32)
ww1 = 1e-2 * np.random.randn(500, 50)
ww2 = 1e-2 * np.random.randn(50, 5)

learning_rate = 1e-1
for t in xrange(20):
  loss, scores, dww1, dww2 = f(xx, yy, ww1, ww2)
  print loss
  ww1 -= learning_rate * dww1
  ww2 -= learning_rate * dww2