[Solved] ECE471 Assignment3 -Classify mnist digits with a convoultional neural network

Classify mnist digits with a convoultional neural network. Get at least 95.5% accuracy on the test test.

006

007

008 Problem Statement Consider the mnist dataset consisting of 50,000 training

009

images, and 10,000 test images. Each instance is a 28 28 pixel handwritten digit

010

011 zero through nine. Train a convolutional neural network for classification using

012 the training set that achieves at least 95.5% accuracy on the test set. Do not

013 explicitly tune hyperparameters based on the test set performance, use a validation

014

015 set taken from the training set as discussed in class. Use dropout and an L² penalty

016 for regularization. Note: if you write a sufficiently general program the next

017 assignment will be very easy.

018

⁰¹⁹ Do not use the built in mnist data class from tensorflow.

020

021

022

Extra challenge (optional) In addition to the above, the student with the fewest

023

024 number of parameters for a network that gets at least 80% accuracy on the test set

⁰²⁵ will receive a prize. There will be an extra prize if any one can achieve 80% on the

026

test set with a single digit number of parameters. For this extra challenge you can

027

028 make your network have any crazy kind of topology youd like, it just needs to be ⁰²⁹ optimized by a gradient based algorithm.

030

031

032

033

034

035

036

037

038

039

040

041

042

043

044

045

046