Neural Network

Implementation of a feed forward neural network with back-propagation. Pretraining done using stacked auto-encoders Implements dropout and L2 regularization to avoid overfitting

---

Dataset format : Train set/Test set - Should be a tuple consisting of input and target -- ( input, target ) Input - Matrix of the size : ( N, M ) where N is the number of samples and M is the number of input neurons Target - Vector of the form : ( N, ) where N is the number of samples

---