Projects     

Description: Using the ImageNet database, implement a smaller version of AlexNet (https://proceedings.neurips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf) for object classification.  The original AlexNet contains 5 convolutional layers + 3 fully-connected (MLP) layers.  This project is meant for high school students who have working knowledge of Python for machine and deep learning.

Implementation: Implement the missing functions in the reduced form of the AlexNet with 3 convolutional layers and 2 MLP layers.  Train the AlexNet so that it can recognize 5 different objects (e.g. dog, bicycle, car, bird, cat).  You (or your TAs) will decide how much training and testing data you should use.  The team with the most accuracy wins.