Description
Objective: Implementation of handwritten number recognition by ANN.
This is our 2nd exercise in a series that deal with the MNIST Database (http://yann.lecun.com/exdb/mnist/). The MNIST Database is a collection of samples of handwritten digits from many people, originally collected by the National Institute of Standards and Technology (NIST), and modified to be more easily analyzed computationally.
Read: “Using neural nets to recognize handwritten digits”
(http://neuralnetworksanddeeplearning.com/chap1.html) .
Use the MNIST data samples (http://yann.lecun.com/exdb/mnist/) for training and testing.
Develop a code in Matlab (or Python) to design a neural network to perform 10 digit classification.
Experiment with 3 different combination of layers and hidden units.
Summarize the results and report them. Include the code you ran with your report.
WHAT TO SUBMIT:
Submit your code, results (error vs. training epoch), and discussions.
