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 course content changes every semester, so each semester's offerings are unique.

CSE 510 Edge Computing and Front-End Computing (Lecture)
Section: DOER
Instructor: David Doermann
Description: The goal is to understand how to fully understand how we can apply machine learning on resource-limited Edge devices such as the internet of things. We will have 4 projects as well as lectures.
Notes: This course is an introduction to those areas of Artificial Intelligence that deal with fundamental issues and techniques of edge computing. The emphasis is on both conventional methods and deep learning for efficient computing. Topics to be covered include convolutional kernels and Gabor filters, advanced and efficient features for localization, efficient feature reduction, efficient learning and classifiers, neural network and deep learning, compressed neural networks, quantized neural network
Prereqs: Linear algebra, calculus, probability theory and programming (Pytorch or Python)
Coreqs: Machine Learning
URL: https://cse.buffalo.edu/~doermann/LinkedInfo/CSE510-Fall20-Syllabus.htm
Instruction Mode: HyFlex
Class #: 24330
Dates: 08/31/2020 - 12/11/2020
Days, Time: TR, 5:30PM-6:45PM
Location: Davis 101, North Campus
Credit Hours: 3.00
Enrollment: 5/15 (5/15 seats reserved for computer science & engineering majors only)
Links: Registration: CSE 510LEC registration number 24330 calendar icon | Course Catalog: CSE 510LEC orange catalog icon
CSE 510 Quantitative equity portfolio management (Lecture)
Section: KEAN
Instructor: Kevin Keane
Description: This course will prepare students to research and implement quantitative equity strategies. This course will provide a self-contained overview, empirical examination, and detailed mathematical treatment of various topics that serve as the foundation of quantitative equity portfolio management. The course presents advanced techniques and applications in return forecasting models, risk management, portfolio construction, and portfolio implementation. Students will construct alpha models (stock performance forecasts), risk models, transaction cost models, and combine these inputs as a mathematical programming problem. The output from the optimization step will then be back tested and analyzed to evaluate strategy results. Reproducible research methods will be emphasized. Student work will be version controlled and shared with the instructor during the semester. Students may use the programming language of their choice (python, R, java, ...). Grading: class participation 10%; homework / mini-projects 60%; final project 30%.
Prereqs: Calculus, matrix algebra, probability, statistics, and computer programming.
Instruction Mode: Remote: real time and recorded
Class #: 25514
Dates: 08/31/2020 - 12/11/2020
Days, Time: TR, 3:55PM-5:10PM
Location: Remote
Credit Hours: 3.00
Enrollment: 2/25
Links: Registration: CSE 510LEC registration number 25514 calendar icon | Course Catalog: CSE 510LEC orange catalog icon
CSE 510 Trustworthy and Explainable AI (Lecture)
Section: SREY
Instructor: Sreyasee Das Bhattacharjee
Description: In this course, we will discuss adversarial learning, analyze explainability as well as the security vulnerability and privacy related issues of different machine learning(ML)/Artificial Intelligence(AI) models, popularly used by the research community. While AI is growingly being employed as an automated decision making tool in several usecase settings like business, education, healthcare, law enforcement, etc., before adopting any such system, it is important for the end users to have a clear understanding of the questions like ‘why the system works?’ than treating it as an omnipotent BlackBox without having any explanation on its trustworthiness. We will review several state-of-the-art research papers to learn about the recent advances in this emerging domain of Trustworthy and Explainable AI, discuss several representative explainable models, learn about different categories of attacks along with a set of certified defenses introduced to evaluate robustness, and finally explore the connections between explainability and trustworthiness in terms of its applications in several domain specific problem settings. * This will satisfy the depth requirement of AI*
Prereqs: CSE 116 and MTH 142 and MTH 309 and (CSE 469 or CSE 455 or CSE 474)
URL: https://cse.buffalo.edu/~sreyasee/CSE4510/
Instruction Mode: HyFlex
Class #: 24806
Dates: 08/31/2020 - 12/11/2020
Days, Time: MWF, 11:30AM-12:20PM
Location: Davis 101, North Campus
Credit Hours: 3.00
Enrollment: 1/20 (1/20 seats reserved for computer science & engineering majors only)
Links: Registration: CSE 510LEC registration number 24806 calendar icon | Course Catalog: CSE 510LEC orange catalog icon
CSE 510 Reinforcement Learning (Lecture)
Section: VERE
Instructor: Alina Vereshchaka
Description: This course is intended for students interested in artificial intelligence. Reinforcement learning is an area of machine learning where an agent learns how to behave in an environment by performing actions and assessing the results. Reinforcement learning is how Google DeepMind created the AlphaGo system that beat a high-ranking Go player and how AlphaStar become the first artificially intelligent system to defeat a top professional player in StarCraft II. We will study the fundamentals and practical applications of reinforcement learning and will cover the latest methods used to create agents that can solve a variety of complex tasks, with applications ranging from gaming to finance to robotics. The course is comprised of assignments, short weekly quizzes, a final project and a final exam.
Notes: Reinforcement Learning
Prereqs: CSE4/574 or CSE4/555 or CSE4/573 or CSE4/568 is recommended to be either completed or taken during the same semester
Instruction Mode: Remote class, in person exam
Class #: 23497
Dates: 08/31/2020 - 12/11/2020
Days, Time: TR, 3:55PM-5:10PM
Location: Remote
Credit Hours: 3.00
Enrollment: 25/40 (14/30 seats reserved for computer science & engineering majors only)
Links: Registration: CSE 510LEC registration number 23497 calendar icon | Course Catalog: CSE 510LEC orange catalog icon
CSE 610 Non-parametric Bayesian Machine Learning (Lecture)
Section: CHAN
Instructor: Varun Chandola
Description: In this course, we will focus on one class of ML methods – non-parametric Bayesian methods. This will be stats and math-heavy course. We will talk about models such as Gaussian Processes, Dirichlet Process Mixture Models, Mixed membership models in general. We will learn about how to learn without making any parametric assumptions about the data. In the unsupervised setting, we will learn about methods that can cluster data without specifying the number of clusters. There will be a semester long project component to the course.
Notes: Non-parametric Bayesian Machine Learning Methods
Prereqs: CSE574 or equivalent
Instruction Mode: HyFlex
Class #: 23883
Dates: 08/31/2020 - 12/11/2020
Days, Time: TR, 11:10AM-12:25PM
Location: Talbrt 107, North Campus
Credit Hours: 3.00
Enrollment: 22/30 (18/30 seats reserved for computer science & engineering majors only)
Links: Registration: CSE 610LEC registration number 23883 calendar icon | Course Catalog: CSE 610LEC orange catalog icon
CSE 610 System Security - Attack and Defense for Binaries (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/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-based buffer overflow, format string vulnerability, return-oriented programming, etc. This class also covers defensive techniques including canary, shadow stack, address space layout randomization, 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.
Notes: Stack-based buffer overflow; Developing Shellcode; Defenses against stack-based buffer overflow; Heap-based buffer overflow; Format string vulnerability; Integer overflow vulnerability; Return-oriented programming.
Instruction Mode: Remote: real time
Class #: 24587
Dates: 08/31/2020 - 12/11/2020
Days, Time: M, 5:20PM-8:10PM
Location: Remote
Credit Hours: 3.00
Enrollment: 7/25 (0/3 seats reserved: force registration only)
Links: Registration: CSE 610LEC registration number 24587 calendar icon | Course Catalog: CSE 610LEC orange catalog icon
CSE 701 Deep Learning on Graphs (Seminar)
Section: SAR
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 Recurrent Neural Networks, Graph Reinforcement Learning, Graph Adversarial Methods, Graph Convolutional Networks, and Graph Autoencoders. 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.
Notes: Deep Learning on Graphs
URL: http://sariyuce.com/F20-701.html
Instruction Mode: Remote: real time
Class #: 20699
Dates: 08/31/2020 - 12/11/2020
Days, Time: W, 6:00PM-8:30PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 11/20 (11/20 seats reserved for computer science & engineering majors only)
Links: Registration: CSE 701SEM registration number 20699 calendar icon | Course Catalog: CSE 701SEM orange catalog icon
CSE 703 Deep Learning for Visual Recognition with Applications to Medical Imaging Analysis (Seminar)
Section: GAO
Instructor: Mingchen Gao
Description: Deep learning is providing exciting solutions for visual recognition problems and is seen as a key method for future applications. This course is a deep dive into the state-of-the-art algorithms in the convolutional neural network (CNN) architectures, image classification, object detection, and segmentation. Medical imaging analysis, as a unique application of computer vision to provide computer-aided analysis, will also be covered. The course will be beneficial to students interested in understanding the massive amount of literature in computer vision and deep learning.
Notes: Deep Learning methods for image classification, object detection, and image segmentation. Applications to medical image analysis will also be discussed.
Prereqs: Require fundamental knowledge about machine learning, computer vision, and deep learning. Prior knowledge about medical imaging is not necessary.
URL: https://cse.buffalo.edu/~mgao8/CSE703.html
Instruction Mode: Remote: real time and recorded
Class #: 20396
Dates: 08/31/2020 - 12/11/2020
Days, Time: M, 9:00AM-10:30AM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 25/25 (25/25 seats reserved for computer science & engineering majors only)
Links: Registration: CSE 703SEM registration number 20396 calendar icon | Course Catalog: CSE 703SEM orange catalog icon
CSE 705 Graph Representation Inferences and Learning (Seminar)
Section: WEN
Instructor: Wen Dong
Description: We live in a complex world with many complex interaction systems, such as neural activities in our brain, the movement of people in an urban system, epidemic and opinion dynamics in social networks, and so on. Learning and making inference inference about the dynamics on these systems has attracted considerable interest since it potentially provides valuable new insights, for example about functional areas of the brain and relevant diagnoses, about traffic congestion and more efficient use of roads, and about where,when and to what extent people are infected in an epidemic crisis. In recent years, big data and deep learning has provided new opportunities to the graph representation inference and learning. In this seminar course, we will be surveying the models, learning and inference algorithms, and applications related to graph representation. This course is inherently multi-disciplinary, hands-on, and research oriented. Participation is a must.
Notes: - Exponential random graph models - Network science - Graph neural networks - Variational Inference - Markov chain Monte Carlo - Ubiquitous computing applications - Text mining applications - Systems biology applications We will be covering the following readings: - Bronstein, M. M., Bruna, J., LeCun, Y., Szlam, A., & Vandergheynst, P. (2017). Geometric deep learning: going beyond euclidean data. IEEE Signal Processing Magazine, 34(4), 18-42. - Hamilton, W. L., Ying, R., & Leskovec
Prereqs: CSE 555 Introduction to Pattern Recognition or CSE 574 Introduction to Machine Learning
Instruction Mode: Remote: recorded not real time
Class #: 24001
Dates: 08/31/2020 - 12/11/2020
Days, Time: F, 4:30PM-7:00PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 20/20 (20/20 seats reserved for computer science & engineering majors only)
Links: Registration: CSE 705SEM registration number 24001 calendar icon | Course Catalog: CSE 705SEM orange catalog icon
CSE 706 Deep Generative Models and Deep Reinforcement Learning (Seminar)
Section: CHE
Instructor: Changyou Chen
Description: This seminar discusses recent developments on deep generative models and deep reinforcement learning.
Notes: Deep Generative Models, Deep Reinforcement Learning
Prereqs: CSE574, CSE676
Instruction Mode: Remote: real time and recorded
Class #: 21005
Dates: 08/31/2020 - 12/11/2020
Days, Time: M, 1:00PM-3:00PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 23/23 (22/23 seats reserved for computer science & engineering majors only)
Links: Registration: CSE 706SEM registration number 21005 calendar icon | Course Catalog: CSE 706SEM orange catalog icon
CSE 708 CSE 708: Cloud Computing and Distributed Systems (Seminar)
Section: DEMI
Instructor: Murat Demirbas
Description: The seminar analyzes recent significant papers on the topic of distributed systems and cloud computing each week. Each student will serve as a presenter for one paper, as a notetaker for the same paper, and as a participant for all the remaining papers. We will meet Monday 11-to-1pm at Davis 113A.
Notes: Distributed systems; Distributed algorithms; Cloud computing; Data center computing
Prereqs: CSE 486/586. It is OK if this is being taken the same semester.
URL: http://www.cse.buffalo.edu/~demirbas/CSE708.html
Instruction Mode: Remote: real time and recorded
Class #: 24567
Dates: 08/31/2020 - 12/11/2020
Days, Time: M, 11:00AM-1:00PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 14/20 (14/20 seats reserved for computer science & engineering majors only)
Links: Registration: CSE 708SEM registration number 24567 calendar icon | Course Catalog: CSE 708SEM orange catalog icon
CSE 712 Knowledge Bases and Ontologies (Seminar)
Section: JAN
Instructor: Jan Chomicki
Description: Ontologies and knowledge bases generalize relational databases by providing high-level, formal descriptions of content that can still be efficiently processed. They find applications in biological and medical sciences.(for example the GO ontology, government, and other areas. The students in this seminar will present papers from the current technical literature and reports or summaries of those papers.
Notes: Specification, application and reasoning with ontologies.
Prereqs: A database course.
Instruction Mode: Remote: real time and recorded
Class #: 23958
Dates: 08/31/2020 - 12/11/2020
Days, Time: T, 10:00AM-11:50AM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 17/18 (17/18 seats reserved for computer science & engineering majors only)
Links: Registration: CSE 712SEM registration number 23958 calendar icon | Course Catalog: CSE 712SEM orange catalog icon
CSE 715 Topics in Software Verification (Seminar)
Section: BHAR
Instructor: Bharat Jayaraman
Description: "... software verification has been the holy grail of computer science for many decades, but now in some very key areas, for example, driver verification, we're building tools that can do an actual proof about the software and how it works in order to guarantee reliability." - Bill Gates, keynote address, WinHEC conference

Approaches to software verification may be broadly classified as code-based and model-based. The former deals directly with the source code whereas the latter deals with a high-level model of the actual code. A number of tools have emerged in the last decade to support these two methodologies, with considerable interest in industry, e.g., Alloy, CodeSurfer, Coq, Frama-C, Isabelle, Java PathFinder, PRISM, PVS, SLAM, SPIN, and UPPAAL. (Bill Gates was referring to the SLAM tool developed at Microsoft in the above quotation.)

At UB, we have been exploring the concept of runtime verification of software systems, combining aspects of both of the above approaches. We are trying to incorporate runtime verification techniques in a state-of-the-art dynamic analysis and visualization tool for Java, called JIVE, which is available as a plug-in for the Eclipse IDE and downloadable from http://www.cse.buffalo.edu/jive.

The reading materials will be drawn from published papers, tutorials, and user manuals of the tools. They will be made available through the Piazza forum to be set up for the seminar.

Grading policy: S/U, as per department policy

Meeting Time and Place: Fridays, 4-7 pm online

Course Credits:

1 credit - class participation + presentation
3 credits - class participation + presentation + verification project
2 credits - same as 3 credits but smaller verification project

Notes: This seminar is devoted to the study of concepts, methodologies, and tools for rigorous software verification. The benefits of a rigorous approach are early error detection, increased programmer productivity and software reliability. Such an approach is today seen as necessary in developing safety-critical systems where software failure can have catastrophic results. Examples include avionics systems, autonomous vehicles, medical devices, and industrial automation.
Prereqs: Graduate Standing in CSE.
Coreqs: None. The instructor will provide an introduction to the underlying concepts in order to make the seminar self-contained.
Instruction Mode: Remote: real time
Class #: 22852
Dates: 08/31/2020 - 12/11/2020
Days, Time: F, 4:00PM-7:00PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 30/30 (30/30 seats reserved for computer science & engineering majors only)
Links: Registration: CSE 715SEM registration number 22852 calendar icon | Course Catalog: CSE 715SEM orange catalog icon
CSE 741 Selected Topics in Emerging Biometrics and IoT Security (Seminar)
Section: WENY
Instructor: Wenyao Xu
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.
Notes: Biometrics (face, fingerprint and iris); IoT Security; Hardware Security; Machine Learning Security.
Prereqs: N/A
URL: https://cse.buffalo.edu/~wenyaoxu/courses/fall2020/CSE741C.htm
Instruction Mode: Remote: real time and recorded
Class #: 24279
Dates: 08/31/2020 - 12/11/2020
Days, Time: W, 10:00AM-12:00PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 20/20 (19/20 seats reserved for computer science & engineering majors only)
Links: Registration: CSE 741SEM registration number 24279 calendar icon | Course Catalog: CSE 741SEM orange catalog icon