CSCI-GA.3033
Special Topics: Efficient AI Computing: Algorithm and Implementation
fall 2025
The course will focus on recent advancements in the design of efficient neural networks, specifically on how to create and optimize AI models for improved performance, and resource efficiency. Students will explore essential techniques such as pruning, quantization, and model distillation across different model architectures like CNNs, RNNs, Transformers, and LLMs. These techniques aim to reduce computational complexity while preserving accuracy. Additionally, the course will cover efficient training and inference methods, including distributed computing, parallelism, and low-precision computation, essential for deploying AI on resource-constrained platforms. Lastly, students will gain a foundational understanding of computer architectures and learn how to deploy AI algorithms on actual edge devices.
Lecture Time: Wednesday 7:10-9:10pm EST (Zoom)
Lecture Location: Room 275, NYU Global Center for Academic and Spiritual Life (GCASL)
Readings: Course slides and papers
Suggested readings: Goodfellow, Ian. "Deep learning." (2016). https://www.deeplearningbook.org/
Evaluation Breakdown:
-
Assignments (30%): total three of them, each counts 10%
-
In-course quiz (15%)
-
Midterm (25%)
-
Final project (30%)
-
Proposal (1 page) 5%
-
Final presentation 15%
-
Final report 10%
-
Late Submission Policy:
- A 10% deduction will be applied to the original grade if submitted within 24 hours; otherwise, a 30% deduction will be applied.
Contact:
- For questions related to course materials, use efficientaiaccelerator@gmail.com
- When you send your email, please start the email title with three categories to indicate the type of the question: [Algorithm], [System], [Others].
-
For other inquiries, personal matters, or emergencies, you can email me at sai.zhang@nyu.edu
Instructor
Grader
Yunhai Hu
Course Schedule
Date | Topic | Logistics |
Sep 3 | Lecture 0: Course Introduction Lecture 1: Basic topics of DNN | |
Sep 10 | Lecture 2: Convolutional Neural Networks | |
Sep 17 | Lecture 3: Intro to Transformers and Large Models | |
Sep 24 | Lecture 4: Neural Network Pruning | Assignment 1 is posted on Brightspace |
Oct 1 | Lecture 5: Neural Network Quantization | |
Oct 8 | Lecture 6: Distillation, Low Rank Decomposition and Neural Architecture Search | Assignment 1 due Assignment 2 is on Brightspace |
Oct 15 | Lecture 7: Efficient Algorithm for Large Model | |
Oct 22 | Lecture 8: Efficient Neural Network Training | Assignment 2 due Assignment 3 is on Brightspace |
Oct 29 | In-class midterm exam | Project proposal due |
Nov 5 | Lecture 9: Distributed System for DNN Training and Inference | |
Nov 12 | Lecture 10: Machine Learning System for Large Model | Assignment 3 due |
Nov 19 | Lecture 11: AI Accelerator Introduction and CNN Accelerators | |
No Class | Legislative Friday | |
Dec 3 | Lecture 12: Transformer & LLM Accelerators | |
Dec 10 | Lecture 13: Guest Lecture | |
Dec 17 | Final Presentation |