Problem Statement Consider the mnist dataset consisting of 50,000 training
images, and 10,000 test images. Each instance is a 28 28 pixel handwritten digit
zero through nine. Train a (optionally convolutional) neural network for
classification using the training set that achieves at least 95.5% accuracy on the test
set. Do not explicitly tune hyperparameters based on the test set performance,
a validation set taken from the training set as discussed in class. Use dropout and
an L2 penalty for regularization. Note: if you write a sufficiently general program
the next assignment will be very easy.
Do not use the built in mnist data class from tensorflow.
Extra challenge (optional) In addition to the above, the student with the fewest
number of parameters for a network that gets at least 80% accuracy on the test set
will receive a prize. There will be an extra prize if any one can achieve 80% on the
test set with a single digit number of parameters. For this extra challenge you c
make your network have any crazy kind of topology you’d like, it just needs to be
optimized by a gradient based algorithm.
