Deep Learning Boot Camp
Spring 2025
Jan 24, 2025
-
May 2, 2025
Checking your registration status...
To access the program content, you must first create an account and member profile and be logged in.
You are registered for this program.
Registration Deadlines
Jan 17, 2025
-
People with data science experience, but are not Erdős alumni. You MUST complete a data science assessment to be enrolled.
Jan 24, 2025
-
Erdős members / alumni who have successfully completed a prior Erdős Data Science Boot Camp Project
-
Category
Advance, Supplemental, Self-Directed, Project-Based, Boot Camp
Overview
Welcome to deep learning! Each week, you'll complete assigned readings from 2 deep learning books. During the first few weeks, there will be weekly meetings with the instructors and all attendees on Zoom. As you progress more into the material and your projects, you will meet according to your group schedule.
In order to receive a deep learning certificate, you must submit a (team-based) final project by the date on schedule below.
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
Associate Director of Erdős
Office Hours:
as needed
Email:
Preferred Contact:
Slack
Slack is the best way to contact me!
Marcos Ortiz
Lead Deep Learning TA
Office Hours:
as needed
Email:
Preferred Contact:
Slack
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 9
RivusVox Editor
Zachary Bezemek,Francesca Balestrieri
RivusVox Editor: the world's first near-live zero-shot adaptive speech editing system
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
Schedule
Click on any date for more details
Deep Learning Orientation
Jan 24, 2025 at 05:00 PM UTC
EVENT
Deep Learning Project Pitch Day
Feb 14, 2025 at 09:00 PM UTC
EVENT
Deep Learning Live Review
Jan 31, 2025 at 09:00 PM UTC
EVENT
Deep Learning Class Networking Event
Feb 21, 2025 at 09:00 PM UTC
EVENT
Deep Learning Live Review
Feb 7, 2025 at 09:00 PM UTC
EVENT
Deep Learning Project Showcase
May 2, 2025 at 04:00 PM UTC
EVENT
Please check your registration email for program schedule and zoom links.
Project/Homework Deadlines
Feb 28, 2025
10:00 PM UTC
Deep Learning Project Teams and Topic Due Date
Project description, dataset description, stakeholders, KPIs
Mar 7, 2025
10:00 PM UTC
Deep Learning Weekly Update Due
Basic exploratory data analysis of data; Discussion of preprocessing techniques needed
Mar 14, 2025
09:00 PM UTC
Deep Learning Weekly Update Due
Describe model architecture decisions for baseline model and deep learning model
Mar 21, 2025
09:00 PM UTC
Deep Learning Weekly Update Due
Baseline model performance
Mar 28, 2025
09:00 PM UTC
Deep Learning Weekly Update Due
Fully preprocessed data (for DL model); Deep Learning model performance (iteration 1); Discussion of what went wrong and how to fix it
Apr 4, 2025
09:00 PM UTC
Deep Learning Weekly Update Due
Deep Learning model performance (iteration 2); Discussion of what went wrong and how to fix it
Apr 18, 2025
09:00 PM UTC
Deep Learning Weekly Update Due
Deep Learning model performance (iteration 3); Discussion of what went wrong and how to fix it
Apr 25, 2025
09:00 PM UTC
Deep Learning Final Project Due
Due date for project