Deep Learning Boot Camp
Spring 2024
Feb 2, 2024
-
May 3, 2024
I'm a paragraph. Click here to add your own text and edit me. It's easy.

Checking your registration status...
You are registered for this program.
Registration Deadlines
May 4, 2024
-
Erdős members / alumni who have completed a prior Erdős Data Science Project
-
-
Category
Advance, Supplemental, Self-Directed, Mini-Course
Overview
This is a self-paced deep learning boot camp, using the FastAI book as the foundation (http://course.fast.ai). It is suggested you take 12-15 weeks to go through the material. If possible, you should meet with others to have a weekly discussion group on the material.
In order to receive a deep learning certificate, you must submit a (team-based) final project by **May 03, 2024**.

Click here to be invited to the slack organization: The Erdős Institute
Click here to access the slack channel: #slack-channel
Organizers, Instructors, and Advisors
Lindsay Warrenburg
Lead Instructor
Office Hours:
as needed
Email:
Preferred Contact:
Slack
Participants should feel free to Slack me with any questions or comments!
Objectives
- Learn the basics of deep learning
- Understand how deep learning is used in industry
- Feel comfortable with deep learning code (PyTorch and FastAI)
Project Examples
TEAM 3
Taxi Demand Forecasting
Ngoc Nguyen, Li Meng, Sriram Raghunath, Nazanin Komeilizadeh, Noah Gillespie, Edward Ramirez

Knowing where to go to find customers is the most important question for taxi drivers and ride hailing networks. If demand for taxis can be reliably predicted in real-time, taxi companies can dispatch drivers in a timely manner and drivers can optimize their route decision to maximize their earnings in a given day. Consequently, customers will likely receive more reliable service with shorter wait time. This project aims to use rich trip-level data from the NYC Taxi and Limousine Commission to construct time-series taxi rides data for 63 taxi zones in Manhattan and forecast demand for rides. We will explore deep learning models for time series, including Multilayer Perceptrons, LSTM, Temporal Graph-based Neural Networks, and compare them with a baseline statistical model ARIMAX.
First Steps/Prerequisites
Program Content
I'm a paragraph. Click here to add your own text and edit me. It's easy.
Course materials are available on github through the following link:
github message for user
Textbook/Notes
DataBoard
Demo for generating synthetic data
Jim Schwoebel, Engineering Manager at Verily, shows his new product. If you are interested in generating your own synthetic dataset for your project, then please contact Jim and Roman on slack.
Project/Homework Instructions
I'm a paragraph. Click here to add your own text and edit me. It's easy.
Schedule
Click on any date for more details
Deep Learning Orientation
Feb 2, 2024 at 05:00 PM UTC
EVENT
Aware Corporate Challenge Introduction
Mar 1, 2024 at 08:00 PM UTC
EVENT
Please check your registration email for program schedule and zoom links.
Project/Homework Deadlines
Feb 2, 2024
10:00 PM UTC
Deep Learning Registration Form
This is used to gain access to Slack / Github and to help find teams in similar time zones
Feb 9, 2024
02:34 PM UTC
Deep Learning Group Formation
This is your study group team and your project team
May 3, 2024
09:00 PM UTC
Deep Learning Final Project Due
Click on this box to submit project