Course Description
Welcome to Deep Learning! Over the past few years, Deep Learning has become a popular area, with deep neural network methods obtaining state-of-the-art results on applications in computer vision (Self-Driving Cars), natural language processing (Google Translate), and reinforcement learning (AlphaGo). These technologies are having transformative effects on our society, including some undesirable ones (e.g. deep fakes).
This course is there to give students a practical understanding of how Deep Learning works, how to implement neural networks, and how to apply them ethically. We introduce students to the core concepts of deep neural networks and survey the techniques used to model complex processes within the contexts of computer vision and natural language processing.
Throughout the course, we emphasize and require students to think critically about potential ethical pitfalls that can result from mis-application of these powerful models. The course is taught using the Tensorflow deep learning framework.
Location
Granoff Ctr for Creative Arts 110
Schedule
Tuesday and Thursday, 9:00-10:20am
Instructor
Prof. Eric Ewing
Most Recent Lecture
Most Recent Assignment
Lectures
Weeks 1-3: Foundations of Neural Networks
- 2025-09-4Welcome to Deep Learning
- 2025-09-9Machine Learning
- 2025-09-11Perceptrons and MLPs
- 2025-09-16Optimization, Gradients, and Losses
- 2025-09-18Optimizers and Hyperparameter Tuning
- 2025-09-23Hyperparameter Tuning
Weeks 4-5: Convolutional Neural Networks
- 2025-09-25Convolutions
- 2025-09-30CNNs
- 2025-10-2ResNet and Adversarial Learning
Weeks 6-8: Learning with Sequential Data
- 2025-10-7Learning with Sequential Data
- 2025-10-9RNNs and LSTMs
- 2025-10-14Seq2Seq
- 2025-10-16High Performance Computing (Oscar Tutorial)
- 2025-10-21Transformers and LLMs
- 2025-10-23Large Language Models and Generative AI
- 2025-10-28Autoencoders and VAEs
Weeks 9-11: Unsupervised Learning and Reinforcement Learning
- 2025-10-30Image Generation and GANs
- 2025-11-4Diffusion Models
- 2025-11-6Geometric Deep Learning
- 2025-11-11Reinforcement Learning
- 2025-11-13Policy Gradient Methods
- 2025-11-18PPO
- 2025-11-20GRPO and LLMs
- 2025-11-25Self-Supervised Learning
Weeks 12-13: Looking Forward
- 2025-12-2End-to-End Learning
- 2025-12-4The Future of AI
Assignments
Assignment 1: Introduction and Mathematical Foundations
Assignment 2: Introduction to Numpy and Tensorflow
Assignment 3: BERAS
Assignment 4: CNNS
Assignment 5: Language Modeling
CSCI 1470 Deep Learning Final Project
A semester-long research project where you'll apply deep learning to solve a real problem. Work in teams of 3-4 to either re-implement a research paper or develop a novel solution, gaining hands-on experience in research methodology, experimentation, and presentation.
Deep Learning Day 2025
Celebrate Your Hard Work and Present Your Research!
Date
December 11, 2025
Duration
9:15 AM - 12:15 PM
Location
Third Floor Atrium
Watson Sr. Center for Information Technology (CIT)
Two Presentation Sessions
Click on a session to view group assignments and search for your team
Important Resources
Project Timeline
Team Formation Deadline
Form your team (3-4 people) or let us assign you a team. Submit the form to indicate your preference.
Final Team Assignments
Your mentor TA will be assigned. Check for the announcement to see your team composition.
Project Check-in #1 (Week of Nov 3-7)
Meet with your mentor TA for a brainstorming session. Come prepared with 2-3 project ideas and discuss feasibility and scope.
Project Proposal Due
Submit your finalized project idea. Late submissions receive a 2% grade deduction.
Intermediate Project Report Due
Submit a 2-page outline detailing your plan, methodology, data, and GitHub repo link. Include your outline with your mentor TA.
Project Check-in #2 (Week of Dec 1)
Final check-in meeting with mentor. Submit a one-page reflection on progress, challenges, and next steps.
Deep Learning Day
Celebrate your work! Present your poster to peers and explore other projects. Prepare a ~2 minute presentation.
Final Submission Deadline
Hard deadline at 10 PM. Submit your poster (JPG), code (GitHub), and final writeup. No late days allowed.
Course Timeline
Resources
Guides and Tutorials
Working Remotely
Department Resources
Expedition Team
Do not email sensitive information, including Health Services & Dean's Notes, to any HTAs, UTAs, or STAs.
Lead Geologist

Eric Ewing
he/him
Senior Excavators

Armaan Patankar
he/him
Mining Specialists

Johnny Elias
he/him

Narek Harutyunyan
he/him

Sreedevi Prasad
she/her

Maria Wang
she/her

Sophia Li
she/her

Jacob Hirschhorn
he/him

Matthew Prenovitz
he/him