CMPSC 448 Spring 2022: Machine Learning

Course Information

Instructor

Rui Zhang
Office Hour: MWF 10 - 11am (i.e., between two classes, outside classrooms)

Lecture Time and Location

Section 1: MWF, 9:05-9:55 am @ Steidle Building 114
Section 2: MWF, 11:15-12:05 pm @ Osmond Lab 101

Sarkar Snigdha Sarathi Das, Office Hour: 5-7pm Tuesdays
Ranran Haoran Zhang, Office Hour: 4-6pm Wednesdays
Yusen Zhang, Office Hour: 4-6pm Thursdays

Course Syllabus

Detailed syllabus is avaialbe here.

Course Goals and Objectives

The goal of this course is to introduce data analysis from the machine learning perspective, in particular how to design and evaluate data-driven solutions for real problems in different domains. Students will gain familiarity with the workings of common machine learning models and will learn how noise and bias in the data affect their results. The course assumes programming skills in Python and knowledge in linear algebra, calculus, basic probability and statistics.

Prerequisites

STAT 318 or STAT 414 and CMPSC 122 or prior programming experience. You are expected to have a good understanding of Linear Algebra, Multivariate Calculus, Probability and Statistics, and Programming Skills. We will cover some background material on these topics early in the lectures. However, it is not meant to replace these regular prerequisite courses. For programming skills, you are expected to feel comfortable processing and analyzing data in Python and be familiar with basic algorithmic design and analysis.

Textbook

(CIML)A Course in Machine Learning by Hal Daumé III.
(RLAI)Reinforcement Learning: An Introduction by Sutton and Barto.
(MML)Mathematics For Machine Learning by Marc Peter Deisenroth, A Aldo Faisal, and Cheng Soon Ong.
Pattern Recognition and Machine Learning by Christopher Bishop.
Machine Learning: A Probabilistic Perspective by Kevin Murphy.
Elements of Statistical Learning by Hastie, Tibshirani, Friedman.

Course Schedule

Date	Topic	Material / Reading	Event	Due
Part 1: The Basics of Machine Learning and Background
Week 1 Monday Aug 22	Introduction & Logistics [slides]	CIML 1.1, 1.2, 1.4
Wednesday Aug 24	The Processes of Learning [slides]	CIML 2
Friday Aug 26	The Processes of Learning [slides]	CIML 2, 5.6, 5.9	HW 1 Out
Week 2 Monday Aug 29	Basic Convex Optimization [slides]	MML 2, 3, 4, 5, 6, 7
Wednesday Aug 31	Basic Convex Optimization [slides]	MML 2, 3, 4, 5, 6, 7
Friday Sept 2	Basic Linear Algebra [slides]	MML 2, 3, 4, 5, 6, 7
Part 2: Supervised Learning
Week 3 Monday Sept 5	Labor Day - No Class
Wednesday Sept 7	Linear Regression [slides]	CIML 7.1, 7.2, 7.3, 7.4, 7.5, 7.6
Friday Sept 9	Linear Regression [slides]	CIML 7.1, 7.2, 7.3, 7.4, 7.5, 7.6	HW 2 Out
Week 4 Monday Sept 12	Regularization for Linear Regression: Ridge and Lasso [slides]	CIML 7.1, 7.2, 7.3, 7.4, 7.5, 7.6		HW 1 Due
Wednesday Sept 14	Nearest Neighbors [slides]	CIML 3.1, 3.2, 3.3, 3.5
Friday Sept 16	Perceptron and Neural Networks [slides]	CIML 4.1, 4.2, 4.3, 4.4, 4.5, 4.7, 10.1
Week 5 Monday Sept 19	Logistic Regression [slides]	CIML 9.6
Wednesday Sept 21	Logistic Regression [slides]	CIML 9.6
Friday Sept 23	Support Vector Machines [slides]	CIML 7.7	HW 3 Out
Week 6 Monday Sept 26	Support Vector Machines [slides]	CIML 7.7		HW 2 Due
Wednesday Sept 28	Support Vector Machines [slides]	CIML 7.7
Friday Sept 30	Decision Trees [slides]	CIML 1.3
Week 7 Monday Oct 3	Ensemble: Bagging and Boosting [slides]	CIML 13
Wednesday Oct 5	Ensemble: Bagging and Boosting [slides]	CIML 13
Friday Oct 7	Ensemble: Bagging and Boosting [slides]	CIML 13
Week 8 Monday Oct 10	Midterm Review			HW 3 Due
Wednesday Oct 12	Midterm - No Class			Midterm Exam Due
Friday Oct 14	Midterm - No Class
Part 3: Unsupervised Learning
Week 9 Monday Oct 17	Clustering [slides]	CIML 3.4, 15.1, 16.1, 16.2, 16.3
Wednesday Oct 19	Clustering [slides]	CIML 3.4, 15.1, 16.1, 16.2, 16.3
Friday Oct 21	Expectation–Maximization [slides]	CIML 3.4, 15.1, 16.1, 16.2, 16.3	HW 4 Out
Week 10 Monday Oct 24	Principal Component Analysis [slides]	CIML 15.2
Wednesday Oct 26	Principal Component Analysis [slides]	CIML 15.2
Friday Oct 28	Principal Component Analysis [slides]	CIML 15.2
Week 11 Monday Oct 31	Matrix Factorization [slides]	Koren et al., 2009
Wednesday Nov 2	Matrix Factorization [slides]	Koren et al., 2009
Friday Nov 4	Matrix Factorization [slides]	Koren et al., 2009
Part 4: Reinforcement Learning
Week 12 Monday Nov 7	Bandits [slides]	RLAI 2		HW 4 Due
Wednesday Nov 9	Bandits [slides]	RLAI 2
Friday Nov 11	Markov Decision Processes [slides]	RLAI 3	HW 5 Out
Week 13 Monday Nov 14	Markov Decision Processes [slides]	RLAI 3
Wednesday Nov 16	Dynamic Programming for MDP [slides]	RLAI 4
Friday Nov 18	Dynamic Programming for MDP [slides]	RLAI 4
Week 14	Thanksgiving - No Class
Week 15 Monday Nov 28	Monte Carlo for MDP [slides]	RLAI 5, 6
Wednesday Nov 30	Temporal Difference [slides]	RLAI 5, 6
Friday Dec 2	Temporal Difference [slides]	RLAI 5, 6
Part 5: Advanced Topics
Week 16 Monday Dec 5	[slides]			HW 5 Due
Wednesday Dec 7	[slides]
Friday Dec 9	[slides]
TBD				Final Exam Due