Description
tldr: Classify cifar. Acheive performance similar to the state of the art. Classify 005 cifar. Achieve a top-5 accuracy of 80%.
008 Problem Statement Consider the cifar and cifar datasets which contain
009
32 32 pixel color images. Train a classifier for each of these with performance
010 ×
011 similar to the state of the art (for cifar. It is your task to figure out what is state
012 of the art. Feel free to adapt any techniques from papers you read. I encourage you
013 to experiment with normalization techniques and optimization algorithms in this
014
015 assignment. Write a paragraph or two summarizing your experiments. Hopefully 016 you’ll be able to resuse your mnist program
