Algorithms, September 2020 at CIS
- Instructor: David Woodruff
- Lectures: Sun 7-10am Beijing time
- TAs: Jieling Cai and Tianrui Liu
Course Description
We will put new focus on neural networks in this class.
Grading
Grading is based on 3 homeworks each worth 10%, an exam worth 20%, a final project worth 40%, and class participation worth 10%
Latex
We encourage homework solutions, scribe notes, and final projects to be typeset in LaTeX. If you are not familiar with LaTeX, see this introduction.
Lectures
- Intro to classification, neural networks (CNNs, DNNs, RNNs), generalization, GANs
- Convexity, convex functions, linear approximations, gradient descent, online gradient descent
- Projected gradient descent, coordinate descent, second order and Newton methods, momentum, RMSProp, Adam
- Generalization error for neural networks
Problem Sets
- Homework 2 is on gradient descent - ask the TAs for a copy
References
Materials from the following course might be useful in
various parts of this course:
Maintained by David Woodruff