ece471- Assignment 3 Solved

000          ece, Selected Topics in Machine Learning – Assignment 3

001


003

004             tldr: Classify mnist digits with a convoultional neural network. Get at least 95.5% 005            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 you’d 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

047

048

049

050

051

052

053

054

055

056

057

058

059