Giter Club home page Giter Club logo

cis-522-homework's Introduction

CS522: Deep Learning in the Future

This repository contains the homework prompts for CIS-5220 in Spring of 2023.

Each week(ish), we will release a new homework assignment. The assignments will include a prompt (in the README.md file), and Python code. Your assignment will be to complete the missing implementation or improve the existing code, such that it:

  • Passes the unit tests
  • Meets the requirements of the assignment
  • Passes styleguide checks (aka "lint")

If you meet all of these requirements, you will get a passing grade on the assignment.

But wait, there's more!

Once you have passed all unit tests, your code will be automatically submitted to the class-wide leaderboard (https://leaderboard.cis522.com). Surpass our baseline implementation for the assignment, or place in the top 3, and there may be some extra points in your future :)

Assignments

  1. Linear Regression and Gradient Descent. Write a linear regression model from scratch, and see how gradient descent compares to the closed form solution.
  2. Multilayer Perceptrons.

Getting Started

Fork the repository

To begin, fork this repository by clicking the "Fork" button in the top right corner. This will create a copy of the repository in your own account.

image

Each week, we will release new homework to the original repository, or "upstream" repository. You can pull the latest assignment into your fork from the command line, though we recommend using the "Sync" button on the top right of the code page if you aren't comfortable with multi-remote git workflows yet:

image

image

(In other words, click this button to get the latest assignment!)

You may choose to make your codebase private or public.

Create an account on the leaderboard

To submit your code to the leaderboard, you will need to create an account. Create a new account at https://leaderboard.cis522.com and set your username to your PennKey (usually letters, not numbers. e.g., mine is matelsky.)

Once you have signed into your new account, generate and copy your API key, which you can access by clicking the blue button on your homepage, or navigating to the token page.

image

You will need the token for the next step.

Set up your Secrets

In the settings for your new GitHub repository, add a new secret called CIS522_TOKEN with the value of your API key. Go to the "Settings" tab, and then click "Actions" under "Secrets and variables" on the left pane:

image

Click on "New repository secret" and add the token as the value (use the token you copied in the previous step):

image

Click "Add secret" and you're done; pushes to your main trunk branch will now be automatically submitted to the leaderboard!

How to Submit

  • Update submission.json with your team's usernames and info. Don't forget to cite your sources if you used any external references!
  • Push changes to the trunk branch (main) of your repository (if you're working from pull requests, remember to make your pull requests against your fork, not this upstream repo!)
  • Optionally, add detailed attribution text to (new file) ATTRIBUTION.md if you want to explain some of your code attribution more than a line or two in submission.json. (Remember that failing to correctly cite your sources for code is like plagiarising an essay: This is important!)

cis-522-homework's People

Contributors

charonwangg avatar j6k4m8 avatar meet1995 avatar yungtang-chou avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.