000 ece, Selecte Topics in Machine Learning – Assignment 4
001
002
003
004 tldr: Classify cifar. Acheive performance similar to the state of the art. Classify 005 cifar. Achieve a top-5 accuracy of 80%.
006
007
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.
017
018
019
020
021
022
023
024
025
026
027
028
029
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