Neural Network

A 2 layer neural network for predicting bitwise XOR output of a given input. It takes in a randomly generated data set of ten bits and predicts the XOR value. It is trained for 100 epochs with a sample size of 500 data sets. Gradient descent with sigmoid and tanh activation functions were used as the training method including a cross-entropy loss function. Click on the image below to be redirected to the source code on Github!