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 | Lecture |
|---|---|
| 05/28 | Day 1: Course Intro
Welcome to Machine Learning Review of Probability and Linear algebra Day 2:Decision Trees Reading: Chapter 1 of the text book Day 3: Ensemble Methods & Nearest Neighbor Classification Reading: Chapter 3 of the text book Day 4: Perceptron Reading: Chapter 4 of the text book |
| 06/03 | Day 1: Perceptron Convergence Reading: Chapter 4 of the text book Day 2: Loss Functions and Gradient Descent Reading: Chapter 7 of the text book Convex Review Day 3: Gradient Descent Reading: Chapter 7 of the text book Day 4: Probabilistic View of ML Reading: Chapter 9 of the text book Day 5: Naive Bayes Classifier Reading: Chapter 9 of the text book |
| 06/10 | Day 1: Logistic Regression Reading: Part II of notes Day 2: Training Logistic Regression Contd. Day 3: Multi-label Classification Day 4: Neural Networks - Forward Propagation Reading: Chapter 10 of the text book Day 5: Midterm |
| 06/17 | Day 1: Back Propagation Reading: Chapter 10 of the text book Day 2: Back Propagation Contd. Reading: Chapter 10 of the text book Day 3: No class (Juneteenth) Day 4: Multi Label Classificationn Reading: Chapter 10 of the text book Day 5: HyperParameters, finetuning And Optimizers Reading: Chapter 10 of the text book |
| 06/24 | Day 1: Convolution Neural Network (CNN) Day 2: K-Means & Eigen Value Decomposition Day 3: Principal Components Analysis (PCA) Day 4: AutoEncoders & Kernels Reading: Chapter 11 of the text book Day 5: Support Vector Machines (SVM) Reading: Chapter 11 of the text book |
| 07/01 |
Day 1: Recurrent Neural Networks Day 2: Variational Autoencoders Day 3: Prep day for Final exam Day 4: No Class (July 4th) Day 5: Final Exam |
Instructor: Mohammad Nayeem Teli (nayeem at cs.umd.edu)
Office Hours: Wednesday 10:30 AM (Online)
| Name | |
|---|---|
| Michael-Andrei Panaitescu-liess | mpanaite at umd.edu |
| Wednesday | Michael-Andrei: 3:00 - 5:00 PM |
| Friday | Michael-Andrei: 3:00 - 5:00 PM |