Train both a linear model and a neural network to classify handwritten digits from the classic MNIST data set. Compare the performance of the linear and neural network classification models. Visualize the weights of a neural-network hidden layer. Our goal is to map each input image to the correct numeric digit. We will create a NN with a few hidden layers and a Softmax layer at the top to select the winning class.
douglaswchung / mnist-classification Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License