Special Topics

Special Topics courses cover some of our most innovative and promising research directions.  They are often prototypes of new courses that we are developing.

Special Topics courses offer variable course content, so each semester's offerings are unique.

Summer 2023

CSE 701 Sports Video Analysis (Seminar)
Section: RATH
Instructor: Nalini Ratha
Description: This course is an introduction to those areas of Artificial Intelligence that deal with fundamental issues and techniques of analysis of sports events using multimedia analysis, including computer vision and image processing. The emphasis is on physical, mathematical, and information-processing aspects of the media and sensor data analytics. Topics to be covered include video and sensor data collection, analysis for coaches, player feedback for performance enhancement and injury prevention, game highlights, and video summarization. All forms of media: text, sensors, video, and non-visual spectrum sensing Most of the material is based on recently published research papers.
Notes: Automated Analysis of Sporting Event Videos
Prereqs: CSE 573 or CSE 574 or similar and Deep Learning/machine learning.
Instruction Mode: In person
Class #: 13128
Dates: 07/10/2023 - 08/18/2023
Days, Time: TR, 11:00AM-12:20PM
Location: Davis 113A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 15/30 (0/30 seats reserved: force registration only) (Active)
Links: Registration: CSE 701SEM registration number 13128 calendar icon | Course Catalog: CSE 701SEM orange catalog icon
CSE 705 Recent Advances in Deep Learning & Reinforcement Learning (Seminar)
Section: VERE
Instructor: Alina Vereshchaka
Description: This seminar is intended for students interested to explore the recent advances in deep learning and reinforcement learning fields. Deep learning is an area of machine learning (ML) that uses algorithms, based on the artificial neural networks that can learn complex models from the large datasets. Reinforcement learning is an area of ML in which an agent learns how to behave in an environment by performing actions and assessing the results. In this seminar we will discuss some of the latest works in the area of deep learning and reinforcement learning. The course includes paper readings and presentation, class discussions and a semester-long project where you will put these ideas into practice.
Prereqs: CSE 574 or CSE 546 or CSE 573 or CSE 555
Instruction Mode: Remote: real time
Class #: 13156
Dates: 05/30/2023 - 07/07/2023
Days, Time: MW, 4:30PM-5:50PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 17/32 (0/32 seats reserved: force registration only) (Active)
Links: Registration: CSE 705SEM registration number 13156 calendar icon | Course Catalog: CSE 705SEM orange catalog icon

Fall 2023

CSE 610 Special Topics on Mobile Networking and Mobile Sensing (Lecture)
Section: XIE
Instructor: Yaxiong Xie
Description: Nowadays, wireless technologies (cellular, Wi-Fi, mmWave) do not only provide data service but also cater to diverse applications including indoor localization, contact-free activity sensing, medical implant tracking and charging, virtual reality (VR) and autonomous driving. This course introduces the students with fundamentals in mobile networking and the state-of-the-art mobile sensing applications in the Era of Internet-of-Things. Mobile sensing is an active research area which involves wireless communication, signal processing, human computer interaction, machine learning and hardware prototyping. The intrinsic nature of sensor-free and contact-free makes mobile and wireless sensing particularly appealing in current pandemic compared to traditional sensor-based sensing. The latest research in mobile sensing has enabled many novel and exciting applications. For example, Wi-Fi signals can now be employed to differentiate very similar materials such as Pepsi and Coke. You can place your phone on the desk and turn the desk surface into a touch (input) panel with acoustic sensing. We can employ LoRa signals to sense your respiration even 50 meters away with a wall in between without any sensors. We will explore the state-of-the-art of both mobile networking and mobile sensing and make our hands dirty by working on some research projects.
Prereqs: CSE 589LEC Modern Network Concepts
Instruction Mode: In person
Class #: 23199
Dates: 08/28/2023 - 12/11/2023
Days, Time: TR, 2:00PM-3:20PM
Location: Park 440, North Campus
Credit Hours: 3.00
Enrollment: 8/30 (8/30 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 610LEC registration number 23199 calendar icon | Course Catalog: CSE 610LEC orange catalog icon
CSE 702 Deep Learning for Visual Recognition with Applications to Medical Imaging Analysis (Seminar)
Section: GAO
Instructor: Mingchen Gao
Description: Deep learning provides exciting solutions for visual recognition problems and has become a critical method for many applications. As a unique application of computer vision to provide computer-aided analysis, medical imaging analysis will be a focus of the course. Several vital challenges remain while deploying deep learning models in this life-critical area, such as limited training data, distributed medical data, trustworthiness, fairness, transparency, and patient privacy. The course will benefit students interested in understanding the massive literature on medical imaging analysis, computer vision, and deep learning.
Notes: Grading: Only satisfactory (S) and unsatisfactory (U) will be given. Each student will be expected to present 1-2 papers and lead discussions. Students taking two credits need to write a literature review report about a selected topic. Students taking three credits need to complete a course project in a group of up to three students. The project proposal will be in the 7th week, and project representation will be in the final week.
Prereqs: Prerequisites: Require fundamental knowledge about machine learning, computer vision, and deep learning (CSE4/574, CSE4/555, CSE4/573). Prior knowledge of medical imaging is not necessary.
Instruction Mode: In person
Class #: 21956
Dates: 08/28/2023 - 12/11/2023
Days, Time: M, 2:00PM-4:50PM
Location: Obrian 12, North Campus
Credit Hours: 1.00-3.00
Enrollment: 20/20 (0/20 seats reserved: force registration only) (Active)
Links: Registration: CSE 702SEM registration number 21956 calendar icon | Course Catalog: CSE 702SEM orange catalog icon
CSE 703 Deep Learning on Graphs (Seminar)
Section: SARI
Instructor: Ahmet Erdem Sariyuce
Description: Graphs are everywhere. Their scale, rate of change, and the irregular nature pose many new challenges. Deep learning has been shown to be successful in a number of domains, ranging from images to natural language processing. However, applying deep learning to the ubiquitous graph data is non-trivial because of the unique characteristics. This seminar course covers recent papers in the last few years about deep learning on graphs. We will consider graph embeddings, knowledge graphs, graph kernels, graph neural networks, graph convolutional networks, graph adversarial methods. Students will learn the literature on deep learning on graphs, understand the state-of-the-art algorithms on various problems, and be familiar with the recent trends. Course website for Spring'23 edition is here: https://sariyuce.com/S23-705.html (there will be minor changes for Fall 23)
Prereqs: It is assumed that students have a solid background on discrete mathematics and algorithms. Basic research skills like paper reading, critical thinking, problem solving, report writing, communication, and presentation are important as well.
URL: https://sariyuce.com/S23-705.html
Instruction Mode: In person
Class #: 23933
Dates: 08/28/2023 - 12/11/2023
Days, Time: W, 5:00PM-7:50PM
Location: Davis 113A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 20/20 (0/20 seats reserved: force registration only) (Active)
Links: Registration: CSE 703SEM registration number 23933 calendar icon | Course Catalog: CSE 703SEM orange catalog icon
CSE 704 Machine Learning and Cybersecurity (Seminar)
Section: HU
Instructor: Hongxin Hu
Description: In this seminar class, we will discuss the use of machine learning, especially deep learning, for detecting and mitigating cyber threats arising in commercial systems and applications. We will also discuss security issues in machine learning (adversarial attacks and defenses on deep learning, backdoor attacks and defenses on deep learning, Security in Large Language Models including ChatGPT, etc.). Our ability to identify the type of machine learning algorithms that are useful for specific security applications can help us improve our defenses against attacks such as credit card fraud, malware, and spam, and also anticipate the potential attack variants that may arise in the future. In addition to lectures, you’ll participate in hands-on projects that will simulate a cyber threat and defense. You’ll learn how to extract essential features, preprocess data and then identify a suitable suite of machine learning algorithms that can be used to detect and mitigate the cyber threat.
Notes: Machine Learning and Cybersecurity
URL: https://cse.buffalo.edu/~hongxinh/teaching/2023spring/2023spring.htm
Instruction Mode: In person
Class #: 21958
Dates: 08/28/2023 - 12/11/2023
Days, Time: M, 10:00AM-12:50PM
Location: Davis 113A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 20/20 (0/20 seats reserved: force registration only) (Active)
Links: Registration: CSE 704SEM registration number 21958 calendar icon | Course Catalog: CSE 704SEM orange catalog icon
CSE 709 Internet of Things and Mobile Systems (Seminar)
Section: WENY
Instructor: Wenyao Xu
Description: This comprehensive seminar course delves into the burgeoning field of research on mobile and embedded systems (MES). It explores a wide array of subjects, including energy-efficient sensing, battery management, mobile human-computer interfaces (HCI), mobile security, smartphone crowd-sourcing, and much more. Students will engage with these topics through a combination of lectures, paper presentations, and optional projects, gaining valuable insights into the design methodologies, technologies, and applications that are shaping the present and future of mobile and embedded systems. The curriculum has been thoughtfully crafted to cover critical areas such as mobile energy, mobile security, mobile health, mobile HCI, embedded sensing, and embedded computing. By participating in this seminar course, students will not only enhance their understanding of these subjects, but also develop the skills necessary to contribute to this rapidly evolving field.
Notes: No exam.
Prereqs: No
Coreqs: No
Instruction Mode: In person
Class #: 22263
Dates: 08/28/2023 - 12/11/2023
Days, Time: F, 9:00AM-11:50AM
Location: Clemen 19, North Campus
Credit Hours: 1.00-3.00
Enrollment: 33/45 (0/45 seats reserved: force registration only) (Active)
Links: Registration: CSE 709SEM registration number 22263 calendar icon | Course Catalog: CSE 709SEM orange catalog icon
CSE 711 Geometry and Robot Learning (Seminar)
Section: WANG
Instructor: Chen Wang
Description: This course gives a systematic introduction to the geometric principles and computational methods of recovering three-dimensional (3D) scene structure and camera motion from multiple, or a sequence of, two-dimensional (2D) images. The first part of the course provides a complete and unified characterization of all fundamental geometric relationships among multiple 2D images of 3D points, lines, planes, symmetric structures, etc., as well as the associated geometric reconstruction algorithms. Complementary to geometry, the second part of the course introduces the recent progress in supervised or unsupervised learning-based methods for detecting and recognizing local features or global geometric structures in 2D images, for robust and accurate 3D reconstruction. Although the principles and methods introduced are fundamental and general, this course emphasizes applications in robotics, augmented reality, and autonomous 3D mapping and navigation. This course is entirely self-contained, necessary background knowledge in linear algebra, rigid-body motions, image formation, and camera models will be covered in the very beginning.
Notes: The seminar will be project-heavy and will require students to execute a team-based research project (likely in teams of 2-3). The projects will be assigned by the instructors with the hope that successful ones lead to publication or contribution to open-source projects.
Prereqs: Programming concepts. Classic SLAM systems are built in C++ and Rust. Learning-based systems are based on PyTorch. This is a graduate seminar in CSE. The expectation is that students are able to write and debug reasonable software (~1000 LoC) in C++ and Python. Experience with OpenCV, and PyTorch is a plus. Computer Vision. The course will assume a prior course in Computer Vision including basic image processing. Prior experience with the use of deep learning for computer vision is a plus.
URL: https://sairlab.org/cse711f23
Instruction Mode: In person
Class #: 23248
Dates: 08/28/2023 - 12/11/2023
Days, Time: R, 9:30AM-12:20PM
Location: Davis 113A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 8/20 (0/20 seats reserved: force registration only) (Active)
Links: Registration: CSE 711SEM registration number 23248 calendar icon | Course Catalog: CSE 711SEM orange catalog icon
CSE 712 Practical Quantum Computing and Sensor Technologies (Seminar)
Section: SUT
Instructor: Robert Sutor
Description: This seminar focuses on quantum technologies as they are being developed and used across industry and academia. After reviewing the necessary linear algebra and probability, we will examine the key concepts of quantum computing algorithms and their implementations in software development kits such as Cirq and Qiskit. Through critical readings of texts and papers, we will explore Shor’s algorithm and its implications for cybersecurity. Shifting to hardware, we will learn from guest industry experts how qubit hardware is implemented across a broad range of technologies including superconducting, ion traps, and neutral atoms. After quantum computing, we will delve into the implementations of quantum sensors and memories using neutral atoms. Students will complete coding assignments and lead discussions of key papers.
Instruction Mode: In person
Class #: 24220
Dates: 08/28/2023 - 12/11/2023
Days, Time: F, 2:00PM-4:50PM
Location: Davis 113A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 1/29 (0/29 seats reserved: force registration only) (Active)
Links: Registration: CSE 712SEM registration number 24220 calendar icon | Course Catalog: CSE 712SEM orange catalog icon