These are my solutions to the programming assignments of the class CS231n: Convolutional Neural Networks for Visual Recognition. Here we implemented from scracth different neural networks, goinf from simple fully connected layers, to Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNNs and LSTMs). We implemented all the layers in python including the forward and backpropagation pass to compute the gradients. Different losses were implemented also including cross entropy and an svm loss