Welcome to CMSC 422. Machine Learning studies representations and algorithms that allow machines to improve their performance on a task from experience. This is a broad overview of existing methods for machine learning and an introduction to adaptive systems in general. Emphasis is given to practical aspects of machine learning and data mining.
Week Starting  Tuesday  Thursday 

08/29  Course Intro
Welcome to Machine Learning

Decision Trees Reading: Chapter 1 of the text book 
09/05  Nearest Neighbor Classification Reading: Chapter 3 of the text book 
Perceptron Reading: Chapter 4 of the text book 
09/12  Convergence Analysis of Perceptron 
Linear Classifiers, Gradient Descent and Hinge Loss Reading: Chapter 7 of the text book 
09/19  Gradient Descent Part II Reading: Chapter 7 of the text book 
GD (part III)+ Probabilistic View of ML, Naive Bayes Reading: Chapter 9 of the text book 
09/26  Naive Bayes Classifier  Logistic Regression Reading: Part II of notes 
10/03  Logistic Regression br> Reading: Part II of notes 
Multilabel Classification< 
10/10  Midterm  Neural Networks Reading: Chapter 10 of the text book 
10/17  Nonlinear Regression + Back Propagation  Back Propagation Reading: Chapter 10 of the text book 
10/24  Multi Label Classification, Vanishing Gradients, Momentum method Reading: Chapter 10 of the text book 
More Deep Neural networks, CNN 
10/31  Adversarial Robustness + Recurrent Neural Networks  Unsupervised Learning + KMeans, PCA 
11/07  PCA Analysis  AutoEncoders Reading: Chapter 11 of the text book 
11/14  Kernels Reading: Chapter 11 of the text book 
Deep Learning frameworks / GANs 
11/21  Gaussian Mixture Models Reading: Chapter 7 of the text book 
thanksgiving 
11/28  Expectation Maximization Reading: Chapter 16 of the text book 

12/05  Final Presentations I  Final Presentations II 
Instructor: Mohammad Nayeem Teli (nayeem at cs.umd.edu)
Office: IRB 1128
Office Hours: Tuesdays, 4:45 PM  5:30 PM, IRB 1128
Name  

John D Kanu  jdkanu at umd.edu 
Tin Trung Nguyen  tintn at umd.edu 
Tuesday  Tin: 1:00  3:00 PM 
Wednesday  John: 3:00  5:00 PM 
Thursday  Tin: 1:00  3:00 PM 
Friday  John: 3:00  5:00 PM 
Please note that a TA may need to leave 5 minutes before the end of the hour in order to go to his/her class. Please be understanding of their schedules.
Homework  Due Date* 

Homework 1: Warm Up  Tuesday September 06, 2022 
Homework 2: Decision Trees  Tuesday September 13, 2022 
Homework 3: High Dimensional Space  Thursday September 22, 2022 
Homework 4: Linear Models and Perceptron  Thursday September 29, 2022 
Homework 5: Multiclass Classification  Thursday October 20, 2022 
Project 1: Classification  Monday October 31, 2022 
Programming Assignment 1: Multiclass and Linear Models  Tuesday November 15, 2022 
Homework 6: Principal Component Analysis  Friday November 18, 2022 
Project 3: Principal Component Analysis  Saturday December 03, 2022 
Final Project Presentations  In class, December 6 and 8, 2022 
Final Project Presentations (pdf) on ELMS  Thursday December 8, 2022 
Final Project Report  Thursday December 15, 2022 