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 2022

CSE 701 Automated Analysis of Sporting Event Videos (Seminar)
Section: A
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.
Prereqs: CSE 573, CSE 574 or equivalent
Instruction Mode: In person
Class #: 13120
Dates: 07/11/2022 - 08/19/2022
Days, Time: TR, 9:00AM-10:20AM
Location: Knox 14, North Campus
Credit Hours: 1.00-3.00
Enrollment: 25/25 (0/25 seats reserved: force registration only) (Active)
Links: Registration: CSE 701SEM registration number 13120 calendar icon | Course Catalog: CSE 701SEM orange catalog icon
CSE 702 Automated Analysis of Sporting Event Videos (Seminar)
Section: DOER
Instructor: David Doermann
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: This course does NOT qualify as a CSE Project Course, MS-Robotics Projects Course, and MS-AI Capstone course You may NOT take this course if you took the Special Topics 610 course in the Spring of 2022. Registration is limited so please fill out the following force registration form: https://academics.eng.buffalo.edu/force-registration/request
Prereqs: Computer Vision - Machine Learning Background
URL: https://cse.buffalo.edu/~doermann/LinkedInfo/CSE702-Syllabus%20(Summer%202022)
Instruction Mode: In person
Class #: 13274
Dates: 05/31/2022 - 07/08/2022
Days, Time: TR, 10:30AM-1:30PM
Location: Davis 113A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 24/25 (0/25 seats reserved: force registration only) (Active)
Links: Registration: CSE 702SEM registration number 13274 calendar icon | Course Catalog: CSE 702SEM 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 in AI. 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 and methods used in deep learning and reinforcement learning fields. 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
Instruction Mode: Remote: real time
Class #: 13235
Dates: 05/31/2022 - 07/08/2022
Days, Time: MW, 4:00PM-5:20PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 36/36 (0/36 seats reserved: force registration only) (Active)
Links: Registration: CSE 705SEM registration number 13235 calendar icon | Course Catalog: CSE 705SEM orange catalog icon
CSE 711 Malware Detection for Android: Static and Dynamic Analysis (Seminar)
Section: A
Instructor: Lukasz Ziarek
Description: Learn core compiler techniques for static and dynamic analysis. Discover what additional challenges the Android framework and programming model pose for analyzing Android applications. Learn how to extract features for classification of malware using static analysis. The class will focus on reading classic static and dynamic analysis papers as well as cutting edge applications of such techniques to Android -- both at the framework and application levels.
Instruction Mode: In person
Class #: 13112
Dates: 05/31/2022 - 07/08/2022
Days, Time: TR, 9:00AM-10:20AM
Location: Davis 113A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 33/34 (0/34 seats reserved: force registration only) (Active)
Links: Registration: CSE 711SEM registration number 13112 calendar icon | Course Catalog: CSE 711SEM orange catalog icon

Fall 2022

CSE 510 Software Security (Lecture)
Section: ZHAO
Instructor: Ziming Zhao
Description: This course is designed to provide students with good understanding of the theories, principles, techniques and tools used for software and system hacking and hardening. Students will study, in-depth, binary reverse engineering, vulnerability classes, vulnerability analysis, exploit and shellcode development, defensive solutions, etc. to understand how to crack and protect native software. In particular, this class covers offensive techniques including stack-based buffer overflow, heap security, format string vulnerability, return-oriented programming, etc. This class also covers defensive techniques including canary, shadow stack, address space layout randomization, control-flow integrity, etc. A key part of studying security is putting skills to the test in practice. Hacking challenges known as Capture The Flag (CTF) competitions are a great way to do this. In this class the progress of students are evaluated by lab assignment and in-class Capture-The-Flag (CTF) competitions.
Prereqs: CSE 220 Systems Programming
Instruction Mode: In person
Class #: 21607
Dates: 08/29/2022 - 12/09/2022
Days, Time: M, 5:00PM-7:50PM
Location: Nsc 220, North Campus
Credit Hours: 1.00-3.00
Enrollment: 26/60 (0/50 seats reserved: force registration only) (Active)
Links: Registration: CSE 510LEC registration number 21607 calendar icon | Course Catalog: CSE 510LEC orange catalog icon
CSE 701 Deep Learning methods in biometrics (Seminar)
Section: RATH
Instructor: Nalini Ratha
Description: Deep learning is being applied to many machine learning applications. While face recognition has significantly benefited from deep learning, recently other biometrics modalities are also seeing improved results. This course will cover state of the art in biometrics applications using deep learning architectures. The application of the deep learning techniques to various biometric modalities including face, iris, palmprint, gait, speaker recognition and fingerprints will be covered. Many soft biometrics traits such as gender, skin color, hair color, expression, and dress description will also be included. Along with these, the bias in deep learning while handling biometrics will be studied. The deep learning methods have created more problems for biometrics systems such as adversarial attacks. We will study these security issues in deep learning for biometrics systems based on deep learning. Classes will be interaction-based and will require a project in the area of your choice within the subtopics relevant to the course. The students will be encouraged to produce high quality conference papers in this area. Topics for the course:  Introduction to biometrics and Deep Learning  Unconstrained Face Recognition with Deep Learning  Ocular Recognition with Deep Learning.  Multispectral iris Recognition with Deep Learning.  Speaker recognition with deep learning  Gait recognition using deep learning  Deephashing methods for biometrics search  Deep Metric Learning for biometrics  Bias in biometrics with deep learning  Explainability for biometrics with deep learning  Transfer learning in biometrics  Presentation attack detection in biometrics  Adversarial attacks in biometrics systems
Notes: Computer vision, Deep learning background required
Prereqs: CSE 573 and 574 or equivalent
Instruction Mode: In person
Class #: 17998
Dates: 08/29/2022 - 12/09/2022
Days, Time: W, 3:00PM-5:50PM
Location: Davis 338A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 21/34 (0/34 seats reserved: force registration only) (Active)
Links: Registration: CSE 701SEM registration number 17998 calendar icon | Course Catalog: CSE 701SEM orange catalog icon
CSE 702 Robot Perception (Seminar)
Section: DANT
Instructor: Karthik Dantu
Description: Perception is the ability to see and reason about the environment around a robot. Perception is crucial to robotics and complements planning to realize autonomy in modern robotics. This seminar will build on courses in robotics, computer vision and machine learning at UB, and introduce the current state-of-the-art in robot perception. Topics covered will likely include image/video processing, estimation, SLAM, and semantic perception. We will also explore recent topics in research such as perception in dynamic environments, sim2real techniques such as domain adaptation, and perception with provable guarantees. The seminar will have a series of lectures by the faculty followed by talks by students. Deliverables - Research project (primary), survey paper and two assignments. Eligibility - The course will need strong background in Computer Vision, Machine Learning and programming. We expect students to have taken Robotics Algorithms (CSE 568), Computer Vision Image Processing (CSE 573) and optionally Machine Learning (CSE 574). Similarly, students are expected to have strong hands-on experience in vision/robotics. This course WILL be programming heavy and we expect students to be able to write/understand a few thousand lines of code for the course. This course will be taught by Karthik Dantu and Chen Wang.
Notes: - We will not differentiate between students registered for 1 unit to 3 units. If you sign up, please be ready to do all the work
Prereqs: Robotics Algorithms (CSE568) Computer Vision and Image Processing (CSE 573)
Coreqs: Machine Learning (CSE 574)
URL: https://droneslab.github.io/RobotPerception/
Instruction Mode: In person
Class #: 23415
Dates: 08/29/2022 - 12/09/2022
Days, Time: M, 2:00PM-4:50PM
Location: Norton 214, North Campus
Credit Hours: 1.00-3.00
Enrollment: 5/39 (0/39 seats reserved: force registration only) (Active)
Links: Registration: CSE 702SEM registration number 23415 calendar icon | Course Catalog: CSE 702SEM orange catalog icon
CSE 707 Select Topics on Modern Database Systems (Seminar)
Section: ZHAO
Instructor: Zhuoyue Zhao
Description: In this seminar, we will review select topics on the modern database systems, including real-time data analytics, hybrid transaction and analytical processing, approximate query processing, database usability and many other possible topics. We will review and discuss a few papers from the recent data management conferences (SIGMOD, VLDB, ICDE) or journals that investigated new techniques in these directions. We will also study and review the practical implementation in systems and their adoption in the real-world applications.
Notes: The url links to the webpage of the CSE707 Modern Database Systems offered in Fall 2021. The course requirements will be similar, but the list of papers will be different. In addition, we may provide the option of reviewing system designs and/or demonstrating the system implementation instead of reading papers in the areas, where the system implementation is open source and available.
Prereqs: The student should have taken CSE462/562 Database Systems or equivalent that covers the standard relational algebra, database storage, file organization and access methods (including indexing), query processing and optimization, transaction processing, concurrency control and recovery.
URL: https://cse.buffalo.edu/~zzhao35/teaching/cse707_fall21/
Instruction Mode: In person
Class #: 22827
Dates: 08/29/2022 - 12/09/2022
Days, Time: W, 10:00AM-12:50PM
Location: Davis 113A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 18/30 (0/30 seats reserved: force registration only) (Active)
Links: Registration: CSE 707SEM registration number 22827 calendar icon | Course Catalog: CSE 707SEM orange catalog icon
CSE 708 Programming Massively Parallel Systems (Seminar)
Section: MILL
Instructor: Russ Miller
Description: See https://cse.buffalo.edu/faculty/miller/teaching.shtml "Programming Massively Parallel Systems".
Instruction Mode: In person
Class #: 23467
Dates: 08/29/2022 - 12/09/2022
Days, Time: T, 5:00PM-7:50PM
Location: Frnczk 454, North Campus
Credit Hours: 1.00-3.00
Enrollment: 25/25 (0/25 seats reserved: force registration only) (Active)
Links: Registration: CSE 708SEM registration number 23467 calendar icon | Course Catalog: CSE 708SEM orange catalog icon
CSE 709 Selected Topics in Internet of Things Cybersecurity and Biometrics (Seminar)
Section: WENY
Instructor: Wenyao Xu
Description: Course Description: This seminar course concentrates on the discussion of emerging biometrics and IoT security systems. After reviewing traditional biometrics, a set of emerging biometrics (e.g., soft biometrics, behavioral patterns, etc.) will be in-depth discussed. Also, the seminar will discuss recent research work on mobile user authentication, particularly focusing on biometrics-based approaches. By the end of the seminar, students will learn how to evaluate (i.e., performance metrics) and design user authentication systems using biometrics.
Instruction Mode: In person
Class #: 23810
Dates: 08/29/2022 - 12/09/2022
Days, Time: F, 9:00AM-11:50AM
Location: Frnczk 422, North Campus
Credit Hours: 1.00-3.00
Enrollment: 30/30 (0/30 seats reserved: force registration only) (Active)
Links: Registration: CSE 709SEM registration number 23810 calendar icon | Course Catalog: CSE 709SEM orange catalog icon