This repository contains the code for implementing a simple CNN using lasagne. There are three folders : nooby, standard and binary activation. Nooby contains a naive and simple code for implementing a CNN. Standard contains a more structured way of implementing a CNN which makes the code more flexible to modifications. Binary activation contains a CNN which uses a tailor made op for activation function - this returns 1 or 0 based on the sign of the input, also the gradient is simply passed through if the input is between 0 and 1, else the gradient is killed.