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 

08/28  Course Intro
Welcome to Machine Learning

Decision Trees Reading: Chapter 1 of the text book 
09/04  Ensemble learning 
KNearest Neighbors Reading: Chapter 3 of the text book 
09/11  KNN wrap up / Perceptron 
Reading: Chapter 4 of the text book Convex Review 
09/18  Convergence Analysis of Perceptron
Reading: Chapter 4 of the text book 
Linear Classifiers and loss functions
Reading: Chapter 7 of the text book 
09/25  Gradient Descent
Reading: Chapter 7 of the text book 
GD (part II) and subgradients 
10/02  Naive Bayes Classifier Reading: Chapter 9 of the text book 
Logistic Regression Reading: Part II of notes 
10/09  Logistic Regression Contd.  Midterm 
10/16  Binary to Multilabel Classification (OVR & AVA)/ Logistic Regression Contd. / Multiclass (softmax) 
Neural Networks Reading: Chapter 10 of the text book 
10/23  Neural Networks Contd. Reading: Chapter 10 of the text book 
Nonlinear Regression / Forward Propagation Reading: Chapter 10 of the text book 
10/30  Back Propagation Reading: Chapter 10 of the text book 
Multi Label Classificationn Reading: Chapter 10 of the text book 
11/06  Vanishing Gradients, Momentum method Reading: Chapter 10 of the text book 
Convolution Neural Network (CNN) 
11/13  Convolution Neural Network (CNN) Contd.  Unsupervised Learning  KMeans 
11/20  Thanksgiving Break  
11/27  Principal Components Analysis (PCA)  PCA Contd. Intro to AutoEncoders Reading: Chapter 11 of the text book 
12/04  AutoEncoders & Kernels (SVM) Reading: Chapter 11 of the text book 
Support Vector Machines (SVM) Reading: Chapter 11 of the text book 
Instructor: Mohammad Nayeem Teli (nayeem at cs.umd.edu)
Office: IRB 2224
Office Hours:
Name  Email (at umd.edu) 

Yijun Liang  yliang17 
Isabelle Armene Rathbun  irathbun 
Yan Wen  ywen1 
Wenshan Wu  wwu009 
Monday  Yijun: 9:00  11:00 AM, Wenshan: 1:00  3:00 PM 
Tuesday  Yijun: 9:00  11:00 AM, Isabelle: 4:00  5:00 PM 
Wednesday 
Yan: 10:00 AM  12:00 PM Isabelle: 3:00  5:00 PM 
Thursday 
Wenshan: 12:15  2:15 PM Isabelle: 4:00  5:00 PM 
Friday  Yan: 10:00  12:00 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 05, 2023 
Homework 2: Decision Trees  Thursday September 14, 2023 
Homework 3: High Dimensional Space  Tuesday September 19, 2023 
Homework 4: Linear Models and Perceptron  Monday September 25, 2023 
Project 1: Classification  Saturday September 30, 2023 