Course Description

This course introduces methods on neural networks and deep learning, covering basic machine learning concepts and neural network models, model training and testing, and their applications in computer vision, language processing, and robotics.

Course Schedule

• Instructor: Stan Z. Li and Tao Lin
• Time: Wednesday 10:40 am - 12:15 pm
• Location: YunGu E10-205 (in person), Westlake University
• Teaching Assistants: Jiangbin Zheng, Siyuan Li, Ge Wang, Yufei Huang
• Schedules and Details: Course Schedule and Course Website

News and Updates

[2024-05-22] Assignments hw01-hw11 are all available. Slides of lecture01-lecture06 are updated.

Prerequisites and Materials

• We will be using Numpy and PyTorch in this class, so you will need to be able to program in Python.

• You might need familiarity with essential calculus (differentiation, chain rule), linear algebra, and basic probability.

• You might supplement or expand some knowledge of deep learning through courses online, e.g., LeeDL-Tutorial.

Course Work

• Weekly Homeworks (20%)

  • There are 10 weekly homework assignments (each worth 2%) and hw11 is optional. All answers will be provided at the end of the term.

• Project Proposal (30%)

  • You need to make a [project proposal](./exercises/Project Proposal.docx) with slides (reporting on 05/14/2024). You are encouraged to start early!

• Project Presentation (50%)

  • You need to make a presentation on the project and submit the associated reports (or papers), slides, and codes (or demos).

Documentation

[1] Pattern Recognition and Machine Learning, by Christopher Bishop.

[2] Deep Learning, by I. Goodfellow, Y. Bengio, A. Courville.

[3] Dive Into Deep Learning, by Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola.

[4] Neural Networks and Deep Learning, by Michael Nielsen.

(back to top)