Course Announcements
| Date | Contents |
|---|---|
| 2019-01-11 | Lecture 2 materials and final project guidelines have been posted. |
| 2019-01-08 | The Lectures section has been updated. |
| 2019-01-03 | Please sign up for Piazza and Gradescope! |
| 2018-11-08 | Welcome to the CS205L 2018-2019 Website! |
Summary
A survey of numerical approaches to the continuous mathematics used in computer vision and robotics with emphasis on machine and deep learning. Although motivated from the standpoint of machine learning, the course will focus on the underlying mathematical methods including computational linear algebra and optimization, as well as special topics such as automatic differentiation via backward propagation, momentum methods from ordinary differential equations, CNNs, RNNs, etc.
This course replaces 205A and satisfies all similar requirements.
General Info
- Lectures: Tuesdays and Thursdays, 12:00pm to 1:20pm, Skilling Auditorium.
- TA sections: Fridays, 11:30am to 12:20pm, Herrin T175.
- This course will be recorded, and attendance is encouraged but not required.
- Textbooks: The required textbook for this course is Scientific Computing (Revised 2nd Edition).
- Prerequisites: Math 51; Math 104 or 113 or equivalent or comfort with the associated material.
Course Policy
- 50% Problem Sets:
- Released weekly, no programming assignments
- See the assignments section for more information.
- 50% Pick your own:
- Choose one of the following options for the remaining 50%:
- In-class final exam: held during final exam slot,
- Timed take-home exam: more difficult than in-class final, will be due at the end of the final exam slot,
- Final Project: up to 1 partner allowed (see assignments section for more information),
- A combination of a simpler final project (no partners allowed) for 25%, and one of the two finals for the other 25%.
- To ensure fairness, each option will be evaluated separately.
- Choose one of the following options for the remaining 50%: