CS 260 Machine Learning Algorithms
Winter 2019

Mon/Wed 4:00 pm - 5:50 pm

---

Instructor: Prof. Cho-Jui Hsieh Office location: EVI 284 Email: chohsieh@cs.ucla.edu Office hour: Wednesday 11am-noon Online office hour: Saturday 10am-11am

TA: Patrick Chen TA office hours: Wednesday 2:30-3:30pm @ 3256S-F Online TA : Minhao Cheng Online TA office hour: Saturday 3pm-4pm

---

Announcements

Course Overview

In this course we will introduce some classical and advanced algorithms in machine learning.

Prerequisites
Basic knowledge in numerical linear algebra (singular value decomposition), probability, and calculus (gradient).

Textbooks

There will be no textbook. We suggest the following books if you are interested in studying more advanced topics:

1. Deep Learning (by Ian Goodfellow, Yoshua Bengio, Aaron Courville)

Grading Policy

Grades will be based on the following componenets:

1. Homeworks (50%)
2. Final project (50%)

Tentative Schedule

Date	Topic	Readings and links	Lectures	Assignments
Mon 1/7	Overview of Machine Learning.	DL 5.1	lecture_1
Wed 1/9	Linear Regression and classification	DL 5.1, lecture notes (linear regression)	lecture_2
Mon 1/14	Optimization	DL sec.8	lecture_3
Wed 1/16	Stochastic gradient descent and its variants	DL sec.8	lecture_4
Wed 1/23	Clustering		lecture_5
Mon 1/28	Polynomial nonlinear mapping, Learning theory		lecture_6
Wed 1/30	VC Dimension		lecture_7
Mon 2/4	VC Dimension
Wed 2/6	Kernel methods		lecture_8
Mon 2/11	Tree-based Algorithms		lecture_9
Wed 2/13	(Final project discussion)
Wed 2/20	Neural Network		lecture_10
Mon 2/25	Convolutional Neural Network		lecture_11
Wed 2/27	Recurrent Neural Network, NLP applications		lecture_12
Mon 3/4	Matrix factorization, recommender systems		lecture_13
Wed 3/6	Semi-supervised learning, graph convolution network		lecture_14
Mon 3/11
Wed 3/13