Using Neural Network to classify hand written digits from 0 ~ 9
Given a data set with 5000 handwritten digits and their corresponding labels.
Each training example is a 20 pixel by 20 pixel grayscale image of the digit.
Each pixel is represented by a number indicating the grayscale intensity at that location.
Thus, the neural network will have 400 inputs.
The network will consist of an input layer with 400 inputs, a hidden layer with 25 units, and a softmax layer producing a probability distribution over the ten digits.
Each hidden unit uses a logistic activation function.