Courses

Academic Writing, Norms and Ethics

Course code:GS6001-034

Offered :Autumn 2022

This course aims at presenting the academic writing skills, academic norms and engineering ethics. To begin with, we discuss how to do academic research from the macro perspective. Subsequently, we talk about the academic writing skills and the normative standards in academic writing. Finally, we extend to the engineering ethics that engineers should follow. The course exhibits rich academic writing skills and multiple forms of academic norms by demonstrating standard academic writing paradigms and inappropriate writing cases. Besides, the course draws on many vivid ethical cases to exploit the code of engineering ethics and the consequences of violating engineering ethics.

 

Wavelets and Sparse Signal Processing

Course code:IE7210H

Offered :Autumn 2022

This course aims at presenting the basic theory of wavelet transform-based multimedia signal processing to graduate students. Starting from the basic idea of time-frequency analysis, the course presents the basic definition and property of wavelet transform, filter bank and multi-scale geometry analysis, sparse representation, and other signal processing methods. The course also provides multimedia signal processing tools developed recently based on the idea of wavelet, such as wavelet scattering transform and graph wavelet. It also covers the application method and latest developments of signal processing approaches based on wavelet analysis, fractal and sparse representation in aspect of image and video signal processing.

 

Reinforcement Learning: From Theory to Algorithm

Course code:CS7309

Offered :Autumn 2022

This course will provide a solid introduction to the field of reinforcement learning and students will learn about the core challenges such as how to evaluate and improve policy, how to make model‐free learning and generalization and exploration, also the approaches, including policy iteration, Q‐learning and policy gradient methods. Through a combination of lectures and programming practice, students will become well versed in theory, algorithms and techniques for reinforcement learning.


Fundamentals for Biomedical Signal and Image Processing

Course code:MS330-1

Offered :Autumn 2019

This is a fundamental course of describing biomedical signal and image processing. We expect to cover topics such as Fourier Transform, Sampling, Image Transform, Adaptive Filtering and Biomedical image analysis. Besides, we provide some case studies to help students understand better.

 

Signals and Systems

Course code:EI015

Offered :Spring 2019

This is a fundamental course of describing signals and systems, which is essential and necessary for further study and research in communications, signal processing, circuit design, etc. We expect to cover topics such as linear time-invariant systems, Fourier Series, Fourier Transform, Sampling, Laplace Transform, and Z-Transform.

 

Digital Image Processing

Course code:EE346

Offered :Spring 2016

This is an introductory course to the fundamentals of digital image processing. It emphasizes general principles of image processing, rather than specific applications. We expect to cover topics such as image sampling and quantization, color, point operations, segmentation, morphological image processing, linear image filtering and correlation, image transforms, eigenimages, multiresolution image processing, wavelets, noise reduction and restoration, feature extraction and recognition tasks, and image registration. students will be required to successfully complete several computer projects that are designed to substantially enhance their practical experience.

 

Multimedia Retrieval

Course code:C034709

Offered :Fall 2012

This is an introductory course to the fundamentals of multimedia retrieval. It emphasizes general principles of visual feature extraction, multimedia database and indexing technology. We expect to cover topics such as basic image processing operations, low-level feature extraction, object description and locality sensitive hashing. Students would have basic understanding of multimedia retrieval, image processing and indexing technology, and be required to successfully complete several computer projects that are designed to substantially enhance their practical experience.