COMPSCI 682 Neural Networks: A Modern Introduction


These assignments originally accompany the Stanford CS class CS231n, and are now provided here for the UMass class COMPSCI 682 with minor changes reflecting our course contents. Many thanks to Fei-Fei Li and Andrej Karpathy for graciously letting us use their course materials!


The assignments are due at midnight. You will hand in the assignments electronically through gradescope.
Late Policy:
  • You can use 7 late days, with up to 3 late days per assignment.
  • Once you have used all 7 late days, penalty is 25% for each additional late day.
  • We will use your latest submission for grading and for calculating your late day usage.
  • There is no bonus if you don't use late days at all.
AssignmentDue DateDescription
Assignment #1 9/24(Tue) 11:59pm Image Classification, kNN, SVM, Softmax, Neural Network
Assignment #2 10/15(Tue) 10/17(Thu) 11:59pm Fully-Connected Nets, Batch Normalization, Dropout, Convolutional Nets, Pytorch, TensorFlow
Assignment #3 11/19(Tue) 11/22(Fri) 11:59pm Image Captioning (RNN, LSTM), Network Visualiazation, Fooling Images, Style Transfer, Generative Adversarial Networks