Handwriting-Recognition

A neural network to recognize handwritten digits using a training set is implemented . The neural network will be able to represent complex models that form non-linear hypotheses. The model predicts on a previously predicted model for checking the accuracy.The goal is to implement the feedforward propagation algorithm to use our weights for prediction. The provided script handnn.m is the main script and uses sigmoid.m, predict.m, fmincg.m and displayData.m as accessary functions.