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.

Fall 2021

CSE 510 Philosophy and Artificial Intelligence (Crash Course) (Lecture)
Section: SMIT
Instructor: Staff
Description: The course will be held on the weekend of Oct 2-3. We begin on day 1 with an introduction to how AI works. AI works well in those domains where we can create models based on physical laws or simple rules. But the complexity of the relations involved in many other types of domains prevents successful AI modeling. It is for this reason that we face difficulties when we try to build self-driving cars or to predict the behavior of financial markets. On day 2 we will use what we have learned on day 1 to address the opportunities and limits of AI in modelling and emulating • human consciousness and self-consciousness • human language understanding and conversations (including the Turing test and the Chinese room argument) • social behavior and ethics • transhumanism, life extension, digital immortality We will show that AI will not bring cures for (most) deadly diseases, it will not replace human police with intelligent robots, and – except along certain narrow tracks, including game-playing and image recognition – it will not reach a level of intelligence that surpasses that of human beings. The course is designed to be of interest to both philosophy and computer science and engineering students at both graduate and advanced undergraduate levels.
Notes: It will be taught jointly by Barry Smith (UB Professor of Philosophy and Affiliate Professor of Computer Science) and Jobst Landgrebe (Founder and Managing Director of the AI company Cognotekt (https://www.cognotekt.com/en/). See: http://ontology.buffalo.edu/smith/ https://www.linkedin.com/in/jobst-landgrebe-165103a/
Prereqs: This course is open to both philosophy and computer science and engineering students at both graduate and advanced undergraduate levels.
URL: http://ncorwiki.buffalo.edu/index.php/Philosophy_and_Artificial_Intelligence_(Crash_Course)
Instruction Mode: In person
Class #: 25344
Dates: 08/30/2021 - 12/10/2021
Days, Time: S, Unknown
Location: Park 280, North Campus
Credit Hours: 1.00-3.00
Enrollment: 23/30 (Active)
Links: Registration: CSE 510LEC registration number 25344 calendar icon | Course Catalog: CSE 510LEC orange catalog icon
CSE 510 Software Testing (Lecture)
Section: WANG
Instructor: Weihang Wang
Description: This course focuses on algorithmic software engineering and software testing techniques. The topics will be covered include program tracing, program profiling, slicing, delta debugging, software model checking, symbolic execution, fuzzing, and concolic testing. The goal of this course is to learn fundamental software engineering techniques and their applications in software testing, debugging, maintenance, and software security.
Instruction Mode: In person
Class #: 21191
Dates: 08/30/2021 - 12/10/2021
Days, Time: M, 3:00PM-5:50PM
Location: Grein 116B, North Campus
Credit Hours: 1.00-3.00
Enrollment: 24/24 (24/24 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 510LEC registration number 21191 calendar icon | Course Catalog: CSE 510LEC orange catalog icon
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. The course can be used to satisfy the MS project requirement.
Prereqs: CSE 220 Systems Programming or equivalent
URL: https://zzm7000.github.io/teaching/2021fallcse410510/
Instruction Mode: In person
Class #: 23822
Dates: 08/30/2021 - 12/10/2021
Days, Time: M, 5:00PM-7:50PM
Location: Norton 218, North Campus
Credit Hours: 1.00-3.00
Enrollment: 40/40 (40/40 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 510LEC registration number 23822 calendar icon | Course Catalog: CSE 510LEC orange catalog icon
CSE 610 Human-Computer Interaction and AI (Lecture)
Section: JIN
Instructor: Zhanpeng Jin
Description: This course will teach you about the importance of the human-computer interfaces in the design and development of things people use daily, especially those smart electronic gadgets, and their profounds in human-centered studies, such as smartwatches/wristbands, mobile/wearable devices, smart speakers, touch screen, eye/hand/limb tracking, body gesture, voice assistance, VR/AR/MR, and humanoid robots. We will discuss the capabilities, limitations, and future trends of HCI and other related systems. Moreover, the recent advances in machine learning and AI technologies have enabled new potentials for HCI techniques. For instance, smart sensing technologies will be able to acquire many human behavioral data, which allows providing more user-centric behavioral profiling for more accurate localization, recommendation, and advertising. In this course, you will have access to the most advanced, innovative research ideas in HCI and work on individual and group projects to learn in a hands-on way about the various strategies/ideas of an effective HCI design and how to demonstrate your design’s effectiveness. By the end of this course, students are expected to develop the ability to integrate future-focused HCI thinking into their work, creating faster, simpler, and more intuitive experiences between humans and technology.
Prereqs: None
Coreqs: None
Instruction Mode: In person
Class #: 24026
Dates: 08/30/2021 - 12/10/2021
Days, Time: W, 9:10AM-11:40AM
Location: Baldy 120, North Campus
Credit Hours: 3.00
Enrollment: 19/23 (16/23 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 610LEC registration number 24026 calendar icon | Course Catalog: CSE 610LEC orange catalog icon
CSE 610 Introduction to Digital Media Forensics (Lecture)
Section: LYU
Instructor: Siwei Lyu
Description: The widespread adoption of digital content over traditional physical media such as film has given rise to a number of new information security challenges. Digital content can be altered, falsified, and redistributed with relative ease by adversaries. This has important consequences for governmental, commercial, and social institutions that rely on digital information. The pipeline which leads to ascertain whether an image has undergone some kind of forgery leads through the following steps: determine whether the image is "original" and, in the case where the previous step has given negative results, try to understand the past history of the image. Although the field of information forensics is still young, many forensic techniques have been developed to detect forgeries, identify the origin, and trace the processing history of digital multimedia content. This course provides an overview of information forensics research and related applications. Also, we examine the device-specific fingerprints left by digital image and video cameras along with forensic techniques used to identify the source of digital multimedia files. Finally, an overview of the recent trends and evolution, considering the updated literature in the field, will be provided.
Notes: In this class, you will have hands-on experience of using mathematical tools and programming to expose media forgeries, to play a "Digital media detective".
Prereqs: Machine Learning (CSE 4/574: Intro to ML).
URL: https://cse.buffalo.edu/~siweilyu/DMF_class.html
Instruction Mode: In person
Class #: 23982
Dates: 08/30/2021 - 12/10/2021
Days, Time: R, 10:20AM-12:25PM
Location: Bell 337, North Campus
Credit Hours: 3.00
Enrollment: 3/30 (2/30 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 610LEC registration number 23982 calendar icon | Course Catalog: CSE 610LEC orange catalog icon
CSE 610 Topics in Practical Quantum Computing (Lecture)
Section: REGA
Instructor: Kenneth W. Regan
Description: This course will focus on aspects of quantum computing that connect to existing devices and systems and experiments, apart from the still-remote goal of scaling up a universal quantum computer (capable of implementing Shor's factoring algorithm, for instance). The basic concepts will be treated with attention to the underlying physics, using the new alternate-intro chapter 14 of the second edition of the textbook Introduction to Quantum Algorithms Via Linear Algebra. Quantum circuits will be treated with the concrete focus of freely available simulators such as Qiskit and the IBM Quantum Experience and used to explain quantum teleportation and superdense coding and other fundamentals of quantum communication. Major topics will include entanglement, decoherence, mixed states, operators, quantum random walks and diffusion, the CHSH game and related experimental "paradoxes", and the analysis of concrete quantum advantage.
Notes: Publisher page for the textbook: https://mitpress.mit.edu/books/introduction-quantum-algorithms-linear-algebra-second-edition Chapter 14 will be used in tandem with the previous intro chapters 1--6, then coverage in chapters 7 and 8 will highlight the communication topics. Chapter 16 on quantum walks is also elementary although included in the "advanced" part (the use of walks in chapter 17 is advanced but will not be emphasized). Chapter 14's coverage of other major topics will be supplement
Prereqs: Some prior work with matrices and linear algebra. Theory of computation course not required.
URL: Look for updates at http://www.cse.buffalo.edu/~regan/
Instruction Mode: In person
Class #: 21158
Dates: 08/30/2021 - 12/10/2021
Days, Time: TR, 12:45PM-2:00PM
Location: Baldy 112, North Campus
Credit Hours: 3.00
Enrollment: 4/20 (4/20 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 610LEC registration number 21158 calendar icon | Course Catalog: CSE 610LEC orange catalog icon
CSE 610 Advanced Computer Architecture (Lecture)
Section: SRID
Instructor: Ramalingam Sridhar
Description: The course covers Advanced Topics in Computer Architecture that includes novel computer systems, parallel computing, domain specific systems, and special purpose systems architecture. It prepares for advanced projects/research in computer systems and architecture
Notes: This course will address state of the art hardware/software/systems collaborative projects for diverse applications.
Prereqs: CSE490/590 or equivalent or instructor permission
URL: https://cse.buffalo.edu/~rsridhar/courses/cse610/
Instruction Mode: Remote: not real time
Class #: 23981
Dates: 08/30/2021 - 12/10/2021
Days, Time: R, 3:30PM-6:00PM
Location: Remote
Credit Hours: 3.00
Enrollment: 0/30 (0/30 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 610LEC registration number 23981 calendar icon | Course Catalog: CSE 610LEC orange catalog icon
CSE 701 Deep Learning methods in biometrics (Seminar)
Section: RATH
Instructor: Nalini Ratha
Description: CSE 701 (Fall 2021): Deep Learning methods in biometrics Deep learning is being applied to many machine learning applications. While face recognition has significantly benefited by deep learning, recently other biometrics modalities are also seeing improved results. This course will cover state of the art in biometrics application 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 biometric 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
Prereqs: Deep learning Computer vision Biometrics
Instruction Mode: In person
Class #: 18754
Dates: 08/30/2021 - 12/10/2021
Days, Time: MW, 3:15PM-5:20PM
Location: Davis 338A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 20/20 (19/20 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 701SEM registration number 18754 calendar icon | Course Catalog: CSE 701SEM orange catalog icon
CSE 702 Programming Massively Parallel Systems (Seminar)
Section: MILL
Instructor: Russ Miller
Description: Students will work on a project that is run on a massively parallel compute system, which will be provided through the seminar and by the university. Typically, it is a resource available at CCR (www.ccr.buffalo.edu). Students will choose their own project, subject to the approval of the instructor. The programming will typically utilize either MPI, Open MP, or CUDA. Students will present an overview of their project and computational expectations and will present a final review of status and accomplishments. For more information on the course, please see https://cse.buffalo.edu/faculty/miller/teaching.shtml and scroll down to Seminars.
Prereqs: Graduate Standing.
Coreqs: CSE529 is helpful, but not necessary.
Instruction Mode: In person
Class #: 10688
Dates: 08/30/2021 - 12/10/2021
Days, Time: T, 5:30PM-8:00PM
Location: Baldy 115, North Campus
Credit Hours: 1.00-3.00
Enrollment: 15/15 (15/15 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 702SEM registration number 10688 calendar icon | Course Catalog: CSE 702SEM orange catalog icon
CSE 704 Socialbots: NLP for Social Good (Seminar)
Section: SRI
Instructor: Rohini K. Srihari
Description: The widespread use of language-oriented AI solutions presents new opportunities to have a positive social impact. Much existing work on NLP for social good focuses on detecting or preventing harm, such as classifying hate speech, mitigating bias, or identifying signs of extremist behaviour. However, NLP research also offers the potential for positive, proactive applications that can improve user and public well-being or foster constructive conversations. This seminar focuses on the use of socialbots (conversational AI agents) used for social good. Specific topics include: - Positive Conversation, Prosocial, Empathetic Behaviour - Online Well-Being: Positive Information Sharing (overcome "bubbles") - Building trust in socialbots - Computational Models for Persuasion - Multimodal NLP - Interdisciplinary Perspectives
Prereqs: CSE 535 or CSE 635, CSE 574
Instruction Mode: In person
Class #: 24931
Dates: 08/30/2021 - 12/10/2021
Days, Time: T, 1:50PM-3:20PM
Location: Davis 338A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 14/15 (14/15 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 704SEM registration number 24931 calendar icon | Course Catalog: CSE 704SEM orange catalog icon
CSE 705 Deep Generative Models (Seminar)
Section: WEN
Instructor: Wen Dong
Description: The two types of machine learning models, generative and discriminative models, have their respective pros and cons. A generative model explicitly specifies an inductive prior of how observations are generated probabilistically, thus provides an explanation of the predictions and can handle missing data in a Bayesian framework. Recent advances in deep learning have enabled scalable approaches to modeling complex and high-dimensional data. In this seminar course, we will review various generative modeling techniques, including variational inference, normalizing flow models, generative adversarial networks, and applications in natural language processing, image processing, and reinforcement learning. We will develop on the Deep Generative Models course (https://deepgenerativemodels.github.io/) with an emphasis on understanding the implementations from Github, Paper with Code (paperwithcode.com), and other places.
Instruction Mode: In person
Class #: 21326
Dates: 08/30/2021 - 12/10/2021
Days, Time: F, 1:50PM-3:50PM
Location: Baldy 115, North Campus
Credit Hours: 1.00-3.00
Enrollment: 18/15 (18/15 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 705SEM registration number 21326 calendar icon | Course Catalog: CSE 705SEM orange catalog icon
CSE 706 Selected Topics in Deep Learning (Seminar)
Section: CHEN
Instructor: Changyou Chen
Description: We will discuss some advances topics in deep learning, including deep generative models, deep reinforcement learning, meta learning, self-supervised learning, etc.
Prereqs: Have taken courses in machine learning/deep learning.
Instruction Mode: In person
Class #: 19023
Dates: 08/30/2021 - 12/10/2021
Days, Time: M, 1:50PM-3:50PM
Location: Davis 113A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 23/23 (23/23 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 706SEM registration number 19023 calendar icon | Course Catalog: CSE 706SEM orange catalog icon
CSE 708 Security and Privacy in IoT (Seminar)
Section: BLAN
Instructor: Marina Blanton
Description: This course explores security and privacy issues affecting Internet of Things (IoT) devices. It will consist of reading and presenting recent articles examining the issues. It will also include a research project of students' choice.
Instruction Mode: In person
Class #: 21810
Dates: 08/30/2021 - 12/10/2021
Days, Time: F, 10:25AM-12:30PM
Location: Davis 113A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 20/20 (20/20 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 708SEM registration number 21810 calendar icon | Course Catalog: CSE 708SEM orange catalog icon
CSE 740 Connected and Autonomous Vehicles (CAVs) (Seminar)
Section: QIAO
Instructor: Chunming Qiao
Description: In this seminar, the students will be exposed to various topics related to CAV application and system designs, testing and evaluation. The students will be expected to 1) survey, read and present as well as write papers (both white papers and conference/journal publications) on various topics related to CAVs 2) survey, read and present as well as write codes for CAVs (e.g. Autoware and Apollo) 3) survey, present and develop methodologies, (software) tools, platforms, and facilities for testing and evaluating CAVs. 4) survey, present and conduct experiments, to collect and analyze data 5) define and propose new research directions 6) complete, write and present a course project report
Notes: Working on self-driving cars is considered as "a mother of all AI project" - Tim Cook, CEO of Apple. UB is the leader in CAV related research. We are among a very few universities in northeastern region that has CAVs on campus. In fact, we have two that can run on campus. One is Olli - a self driving shuttle that we use to do testing, the other is Lincoln MKZ car that we can do development. We are working on several projects related to connected and automated transportation systems that can help
Prereqs: strong programming abilities, knowledge of computer networks (esp wireless networks), robotics, AI/ML, data analytics.
Instruction Mode: In person
Class #: 19024
Dates: 08/30/2021 - 12/10/2021
Days, Time: W, 4:10PM-7:00PM
Location: Davis 113A, North Campus
Credit Hours: 1.00-3.00
Enrollment: 20/20 (20/20 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 740SEM registration number 19024 calendar icon | Course Catalog: CSE 740SEM orange catalog icon