cSE 251B Competition

Introduction

In this course, you will learn the fundamentals in deep learning. Part of the learning will be through in-class lectures and take-home assignments, but you will really gain hands-on experience by participating Machine Learning Competitions.

Competition Format

You will participate in the competition via Kaggle in small groups, normally 1-4 people. The project contributes to 40% of the course credits:

5 % milestone report
10 % final report
10 % final presentation
10 % team ranking

In the end, you will write a 4 page report about your project.

Details

In this competition, you will develop deep learning models to forecast the motion of autonomous vehicles. You are given a training set of multiple scenes from 6 cities, each with trajectories recorded at 10HZ. You are asked to forecast 6 seconds of trajectory sequences given 5 seconds inputs.

Competition Page: https://www.kaggle.com/competitions/ucsd-cse-251b-class-competition/overview

Resources

Compute: UC San Diego provides Data Science/Machine Learning platform for this course. You can log in with your Active Directory ID.

In addition, you can apply for student cloud computing credits at Google Cloud and Amazon AWS.

Reference: Argoverse: 3D Tracking and Forecasting with Rich Maps