Homework 3

In this assignment you will practice writing backpropagation code and training Convolutional Neural Networks. The goal of this assignment is as follows:

• understand the architecture of Convolutional Neural Networks and gain experience with training these models on data

Setup

Get the starter code by cloning the hw3 github repository. This can be accomplished by executing the following command:

git clone https://github.com/comp150DL/hw3.git

Setup Virtualenv: If you have not created a virtualenv for handling the python dependencies related to this course, please follow the Virtualenv tutorial.

If you would like to work on the provided AWS instances, please follow the Tufts AWS tutorial for how to connect to your Jupyter Notebook remotely.

To satisfy all software dependencies, start your virtualenv and double check that all required packages are installed:

workon deep-venv
cd  hw3
pip install -r requirements.txt

Download data: Once you have the starter code, you will need to download the CIFAR-10 dataset. Run the following from the hw3 directory:

cd datasets
./get_datasets.sh

Start Jupyter Notebook: After you have the CIFAR-10 data, you should start the Jupyter Notebook server from the hw3 directory. If you are unfamiliar with Jupyter, you should read the Jupyter tutorial.

Submitting your work

To make sure everything is working properly, remember to do a clean run (“Kernel -> Restart & Run All”) after you finish work for each notebook and submit the final version with all the outputs. Once you are done working, compress all the code and notebooks in a single file and submit your archive by emailing to comp150dl@gmail.com. On Linux or macOS you can run the provided collectSubmission.sh script from hw3/ to produce a file hw3.zip (or hw3.tar.gz if zip is not on your system) .

Q1: ConvNet on CIFAR-10 (80 points)

In the Jupyter Notebook ConvolutionalNetworks.ipynb you will implement several new layers that are commonly used in convolutional networks. You will train a (shallow) convolutional network on CIFAR-10, and it will then be up to you to train the best network that you can.

Q2: Make a great CNN (20 points, possible +10 points extra credit)

In the process of training your CNN, you should implement at least two of the suggested strategies to get better performance. You can modify the solver, implement additional layers, use different types of regularization, use an ensemble of models, or anything else that comes to mind. Feel free to try more things for extra credit!