Comp137 Deep Neural Networks @ Tufts

Assignment Policies

• Collaboration: Discussions are highly encouraged, but all work need to be completed by individuals or teams independently. You can communicate your ideas verbally or by handwritten notes, but you cannot share your code or report with each other. If you need to use codes from online resources, you need to download corresponding packages or files and import the functions or classes you want to use. You need to clearly acknowledge the usage of these resources.

• Late submissions: Every student get 3 free tickets representing 3 extra days you can spend on your projects. If all tickets are used up, a late submission gets its points discounted by 50% if it is within 24 hours after the deadline and zero points if it is later. If a group project is late, then it falls to all group members, and everyone's share is calculated separately.

Set up your environment

All assignments requires python programming. Please use Anaconda to manage your python packages. The installation of Anaconda does not require a root user or an administrator.

We will use these packages with their default versions listed below. The versions of the last few packages are not important as long as they work with these packages below.

• python=3.7
• tensorflow=2.3
• scipy=1.5.2
• scikit-learn=0.23
• numpy
• matplotlib

Once you have installed Anaconda, you can create an environment by

conda create -n dnn python=3.7

Then you can enter this environment by

conda activate dnn

Inside the environment you can install tensorflow by

pip install tensorflow==2.3 

You also need to install jupyter notebook, which can be installed by Anaconda.

conda install -c conda-forge notebook

Computing resource

Google cloud credits will be provided through a private channel.

Assignment List

• Assignment 1
• Assignment 2 (to be anounced)
• Assignment 3 (to be anounced)
• Assignment 4 (to be anounced)