We will build a complete neural network using Numpy from scratch on MNSIT handwritten digits dataset.
In this assignment, we'll implement an L-layered deep neural network and train it on the MNIST dataset. The MNIST dataset contains
scanned images of handwritten digits, along with their correct classification labels (between 0-9). MNIST's name comes from the fact that
it is a modified subset of two data sets collected by NIST, the United States' National Institute of Standards and Technology.
In this assignment, you will build a complete neural network using Numpy. You will implement all the steps required to build a network - feedforward, loss computation, backpropagation, weight updates etc.
You will use the MNIST dataset to train your model to classify handwritten digits between 0-9.
The assignment is divided into the following sections:
• Data preparation
• Feedforward
• Loss computation
• Backpropagation
• Parameter updates
• Model training and predictions