MNIST with Multi-Layer Perceptron Notes with Examples
MNIST Multi-Layer Perceptron In this lecture we will build out a Multi Layer Perceptron model to try to classify hand written digits using TensorFlow (a very famous example). Keep in mind that no single lecture (or course!) can cover the vastness that is Deep Learning, I would highly suggest reading MIT's Deep Learning textbook for more information on these topics! Get the Data We will be using the famous MNIST data set of handwritten digits . The images which we will be working with are black and white images of size 28 x 28 pixels, or 784 pixels total. Our features will be the pixel values for each pixel. Either the pixel is "white" (blank with a 0), or there is some pixel value. We will try to correctly predict what number is written down based solely on the image data in the form of an array. This type of problem (Image Recognition) is a great use case for Deep Learning Methods! This data is to Deep Learning what the iris data set is to typic...