EEE: Machine Learning for Signals, Information, and Data
General Information
Instructor: Professor Bahman Moraffah
Office: GWC 333
Office Hours: TTh 10:30-11:30 am or by appointment
Class Meet: TTh 12:00-1:15 pm in SS105
Email: bahman.moraffah@asu.edu
Course Description
This graduate-level course explores the intersection of machine learning with signals, information, and data processing, with a focus on control, optimization, and learning; multimedia applications; Bayesian nonparametrics and deep learning; Bayesian signal processing; and statistical and genomic signal processing. The course aims to provide students with a strong theoretical foundation and practical skills to tackle complex problems in these areas using state-of-the-art machine learning techniques.
Course Policies
Prerequisites:
Basic knowledge of linear algebra, probability, and programming.
Prior coursework in signal processing or data analysis is beneficial but not required.
Collaboration: You are encouraged to work on homework problems in study groups of no more than 3 people; however, you must always write up the solutions on your own, and you must never read or copy the solutions of other students. Similarly, you may use books or online resources to help solve homework problems, but you must always credit all such sources in your writeup and you must never copy material verbatim. Offering and accepting solutions from others is an act of plagiarism, which is a serious offense and all involved parties will be penalized according to the Academic Honesty Policy.
Quizzes and Exams: All quizzes and exams are closed books and notes, a single letter-sized notes sheet (front and back) is allowed.
Scribe: We need volunteers to take notes each class, type them up, and send them to me so they can be uploaded for the entire class. Each student can scribe at most 2 lectures. Scribing is NOT mandatory but it is highly encouraged. To get extra credit, you must take notes and type them in the provided template. Extra points are at the instructor’s discretion and depend on the student's effort. You can download the template here.
Syllabus
Week 1: Introduction to Machine Learning for Signals and Data
Week 2: Information Theory, Optimization, and Learning
Fundamentals of infomration theory Optimization techniques for machine learning Reinforcement learning and control applications
Week 3: Multimedia Signal Processing
Processing and analysis of audio and speech signals Image and video processing techniques Feature extraction and representation for multimedia
Week 4: Bayesian Nonparametrics I
Introduction to Bayesian inference and probabilistic models Dirichlet Process and Gaussian Processes Applications in signal processing
Week 5: Bayesian Nonparametrics II
Hierarchical models and nested processes Bayesian nonparametric clustering and mixture models Case studies in signal and data analysis
Week 6: Deep Learning I
Fundamentals of neural networks and deep learning Training deep neural networks: backpropagation and optimization Convolutional Neural Networks (CNNs) for image processing
Week 7: Deep Learning II
Recurrent Neural Networks (RNNs) and sequence modeling Advanced architectures: LSTM, GRU, and attention mechanisms Applications in multimedia and time-series data
Week 8: Bayesian Deep Learning
Combining Bayesian methods with deep learning Bayesian neural networks and uncertainty quantification Case studies and applications
Week 9: Bayesian Signal Processing
Bayesian filtering and estimation techniques Particle filters and sequential Monte Carlo methods Applications in communications and tracking
Week 10: Communications and Signal Processing
Information theory and coding Signal processing techniques for communication systems Machine learning applications in communication networks
Week 11: Statistical Signal Processing
Statistical models for signal analysis Detection and estimation theory Applications in radar and sonar signal processing
Week 12: Genomic Signal Processing
Introduction to genomic data and bioinformatics Signal processing techniques for genomic data analysis Case studies in genetic and genomic research
Week 13: High-Dimensional Data and Optimization
Challenges of high-dimensional data Optimization techniques for high-dimensional machine learning Applications in image processing and data compression
Week 14: Project Presentations and Case Studies
Week 15: Review and Future Directions
Textbooks
"Pattern Recognition and Machine Learning" by Christopher M. Bishop
"Deep Learning: Foundations and Concepts" by Christopher M. Bishop and Hugh Bishop
"Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
"Bayesian Reasoning and Machine Learning" by David Barber
"Bayesian Nonparametrics: An Alternative to Deep Learning" by Bahman Moraffah
"Elements of Information Theory 2nd Edition" by Thomas M. Cover and Joy A. Thomas
Assessment
|