The MNIST database is a large database of handwritten digits that is commonly used for training various image processing systems. The database is also widely used for training and testing in the field of machine learning.

You have to make a multiclass neural network classifier that classifies each image as corresponding digit. Your code should be flexible enough so that it can model any specification that will be given to you during the demo of assignment. E.g. You could be asked to make a neural network of 2 layers(1 input + 1 hidden + 1 output, input layer is not counted as a separate layer and specified number of nodes(neurons) in the hidden layers say 50) with certain initial weights and then you could be asked to give the values of weight/output after ,say, 3 iteration of some given input. This will ensure correctness of your code even if your accuracy is low.

The weightage of the assignment to the course will be decided later. You will be evaluated on accuracy(40%), correctness(60%).

Plagarism will be heavily penalized. You are not allowed to use nerual network libraries like keras. You can also use matlab but again don't use any built in functions related to neural network.

This assignment is to be done on individual basis.