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
