Assignment 3 EECS 498-007/598-005

In this assignment, you will implement Fully-Connected Neural Networks and Convolutional Neural Networks for image classifcation models. The goals of this assignment are as follows:

• Understand Neural Networks and how they are arranged in layered architectures
• Understand and be able to implement modular backpropagation

• Implement various update rules used to optimize Neural Networks

• Implement Batch Normalization for training deep networks

• Implement Dropout to regularize networks

• Understand the architecture of Convolutional Neural Networks and get practice with training these models on data

Q1: Fully-Connected Neural Network (40 points)

The notebook fully_connected_networks.ipynb will walk you through implementing Fully-Connected Neural Networks.

Q2: Convolutional Neural Network (60 points)

The notebook convolutional_networks.ipynb will walk you through implementing Convolutional Neural Networks.

Steps

1. Download the zipped assignment file

2. Unzip all and open the Colab file from the Drive

Unzip the downloaded folder, and upload the contents to your Google Drive. To open the .ipynb notebook fles in Google Colab, right-click on the fles in Drive and select "Open with Google Colab". No installation is required. For more information on using Colab, please see our Colab tutorial.

1. Open your corresponding *.py from Google Colab and work on the assignment

Work through the notebook, executing cells and writing code in *.py, as indicated. You can save your work, both *.ipynb and *.py, in Google Drive (click “File” -> “Save”) and resume later if you don’t want to complete it all at once. While working on the assignment, keep the following in mind:

• The notebook and the python fle have clearly marked blocks where you are expected to write code. Do not write or modify any code outside of these blocks.
• Do not add or delete cells from the notebook. You may add new cells to perform scratch computations, but you should delete them before submitting your work.
• Run all cells, and do not clear out the outputs, before submitting. You will only get credit for code that has been run.

1. Download and Compress Your Work

Once you complete the notebooks, download the relevant fles and compress them into a single .zip fle. Name the fle using the format:{student_id}_A3.zip. Make sure your .zip fle contains your most up-to-date edits. The .zip fle should include fully_connected_networks.py, convolutional_networks.py , best_overfit_five_layer_net.pth, best_two_layer_net.pth, one_minute_deepconvnet.pth, overfit_deepconvnet.pth for this assignment.

5. Submit your zip file to Cybercampus

Submit your compressed .zip fle on Cybercampus.