Coure Inforamtion
| Instructor | Dr. Lei Yang |
|---|---|
| lyang29@gmu.edu (Urgency by text 949-302-7908) | |
| Lecture Time | Tuesday 16:30 pm – 19:10 PM |
| Lecture Type | Online Sync (Zoom: https://gmu.zoom.us/j/6227755427) |
| Office Hour | Tuesday 15:00 - 16:00 PM (Other time by appointment) |
| Office | # 413, Research Hall Building |
Course Materials
Course materials will be posted before or after the class. No formal textbook is required.
We recommend book “Pattern Recognition and Machine Learning” by Christopher M. Bishop for this course.
Course Description
Machine learning (ML) as a field is now incredibly pervasive with several applications such as homeland security face recognition, self-driving car, social media, bioinformatics, etc. This course provides a broad introduction to machine learning, deep learning, and statistical pattern recognition. It introduces interdisciplinary machine learning techniques such as statistics, linear algebra, optimization, and computer science to create automated systems able to make predictions or decisions without human intervention. This class will familiarize students with a broad cross-section of models and algorithms for machine learning, and prepare students for research or industry application of machine learning techniques. The course also provides students with opportunities to gain hands-on experience with several machine learning tools.
Schedule and Documents
| Lecture | Date | Topic | Documents | Note |
|---|---|---|---|---|
| Section I | Introduction of basics of ML & deep neural networks | |||
| Lecture 1 | Aug 23 | Course Information & Introduction to ML | - Assignment HW #1 | |
| Lecture 2 | Aug 30 | Learning Theory and Types of Learning | ||
| Lecture 3 | Sep 06 | Train Neural Networks | ||
| Lecture 4 | Sep 13 | Deep Convolutional Neural Networks (CNN) | ||
| Lecture 5 | Sep 20 | Reinforcement Learning | - Assignment HW #2 | |
| Section II | ML models and algorithms & interdisciplinary ML techniques | |||
| Lecture 6 | Sep 27 | Natural Langue Processing and Image Classification | ||
| Lecture 7 | Oct 04 | Design of ML Accelerator | ||
| Oct 10 | Fall Break | |||
| Lecture 8 | Oct 18 | Model Compression | ||
| Lecture 9 | Oct 25 | Auto ML Techniques - Neural Architecture Search (NAS) | - Assignment HW #3 | |
| Section III | Design & optimization of applied ML techniques in applications | |||
| Lecture 10 | Nov 01 | Applications of Machine Learning: Recent Advances | ||
| Lecture 11 | Nov 08 | Applied ML for Healthcare Applications | ||
| Lecture 12 | Nov 15 | Applied ML for Other Applications | ||
| Lecture 13 | Nov 22 | Course Project Demonstration (1) | ||
| Lecture 14 | Nov 29 | Course Project Demonstration (2) | ||
| Dec 05 | Reading Days | |||
| Dec 13 | Final Exam |