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.

Winter 2021

We aren't offering any courses in Winter 2021.

Spring 2021

CSE 510 Blockchain Advanced Concepts (Lecture)
Section: BINA
Instructor: Bina Ramamurthy
Description: The blockchain stack has five layers: decentralized application, smart contracts, protocol, operating system, and network layers. This course focuses on the blockchain protocol layer, the support provided by the layers below it, and the algorithms and techniques supporting its design and implementation. Topics include Bitcoin and Ethereum blockchain protocols, state and storage management using Merkle trees; consensus algorithms: proof of work, proof of authority, proof of stake, and practical byzantine fault tolerance methods; scalability issues and solutions: side channel, block size, sharding, network-layer solutions such as Tx and block relays; Universal digital identity and self-management of identity; Confidentiality, security, and privacy methods: zero-knowledge proofs, Zcash shielded transactions; Interoperability among protocols: baseline protocol; tokenization with fungible and non-fungible tokens; accessing external data sources using oracles; Ethereum standards and protocol improvement methods; private, public and permissioned blockchains. Upon completing the course, a student will be able to apply protocol level features in application development and will be able to contribute to blockchain protocol improvements.
Notes: Blockchain protocol level concepts
Prereqs: CSE250 or equivalent data structures and algorithms course.
Instruction Mode: Remote: real time and recorded
Class #: 25092
Dates: 01/25/2021 - 05/07/2021
Days, Time: MW, 12:40PM-2:00PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 0/50 (0/50 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 510LEC registration number 25092 calendar icon | Course Catalog: CSE 510LEC orange catalog icon
CSE 510 Machine Learning for Edge Based Devices (Lecture)
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 deploying machine learning on the 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 networks, deep learning and efficient object detectors, neural architecture search, object tracking, and object recognition.
Notes: Machine Learning for Edge Based Devices
Prereqs: Linear algebra, calculus, probability theory, and programming (Pytorch or Python)
URL: https://cse.buffalo.edu/~doermann/LinkedInfo/CSE510_Spring2021.pdf
Instruction Mode: Remote: real time and recorded
Class #: 23852
Dates: 01/25/2021 - 05/07/2021
Days, Time: TR, 7:05PM-8:20PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 4/30 (4/30 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 510LEC registration number 23852 calendar icon | Course Catalog: CSE 510LEC orange catalog icon
CSE 510 Machine Learning and Society (Lecture)
Section: JOSE
Instructor: Kenneth Joseph
Description: Machine Learning (ML) systems make decisions in all parts of our lives, starting from the mundane (e.g. Netflix recommending us movies/TV shows), to the somewhat more relevant (e.g. algorithms deciding which ads Google shows you) to the downright worrisome (e.g. algorithms deciding the risk of a person who is arrested committing a crime in the future). Whether we like it or not, ML systems are here to stay: the economic benefit of automation provided by ML systems means companies and even governments will continue to use algorithms to make decisions that shape our lives. While the benefits of using algorithms to make such decisions can be obvious, these algorithms sometimes have unintended/unforeseen harmful effects. This class will look into various ML systems in use in real life and go into depth of both the societal as well as technical issues. For students who are more technologically inclined, this course will open their eyes to societal implications of technology that such students might create in the future (and at the very least see why claiming “But algorithms/math cannot be biased” is at best a cop-out). For students who are more interested in the societal implications of algorithms, this class will give them a better understanding of the technical/mathematical underpinnings of these algorithms (because if you do not understand, at some non-trivial level, how these algorithms work you cannot accurately judge the societal impacts of an algorithm).
Prereqs: CSE 531 and CSE 574
URL: http://www-student.cse.buffalo.edu/~atri/algo-and-society/spr20/index.html
Instruction Mode: Remote: real time
Class #: 24019
Dates: 01/25/2021 - 05/07/2021
Days, Time: TR, 9:35AM-10:50AM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 1/20 (1/20 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 510LEC registration number 24019 calendar icon | Course Catalog: CSE 510LEC orange catalog icon
CSE 701 Neuro-symbolic Artificial Intelligence (Seminar)
Section: A
Instructor: Hari N. Srihari
Description: We will study a few papers. Students will work on a project to implement a neuro-symbolic system. Students are expected to give regular updates about their progress. The class will meet at a time convenient to all.
Notes: Deep learning is incredibly adept at large-scale pattern recognition and at capturing complex correlations in massive data sets, In contrast, deep learning struggles at capturing compositional and causal structure from data, such as understanding how to construct new concepts by composing old ones or understanding the process for generating new data. Symbolic models, such as probabilistic graphical models, have a complementary strength: They are good at capturing compositional and causal struc
Prereqs: CSE 4/574: Introduction to Machine Learning
Instruction Mode: Remote: real time and recorded
Class #: 23985
Dates: 01/25/2021 - 05/07/2021
Days, Time: W, 3:15PM-5:20PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 5/30 (5/30 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 701SEM registration number 23985 calendar icon | Course Catalog: CSE 701SEM orange catalog icon
CSE 702 Advances in Digital Media Forensics (Seminar)
Section: A
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 to 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: Research advances in digital media forensics
Prereqs: machine learning, image processing
URL: https://cse.buffalo.edu/~siweilyu/DMF_class.html
Instruction Mode: Remote: real time and recorded
Class #: 23863
Dates: 01/25/2021 - 05/07/2021
Days, Time: R, 10:25AM-12:30PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 7/30 (7/30 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 702SEM registration number 23863 calendar icon | Course Catalog: CSE 702SEM orange catalog icon
CSE 703 Advanced Software Security - Techniques and Tools (Seminar)
Section: A
Instructor: Ziming Zhao
Description: This seminar course is designed to provide students with good understandings of the theories, principles, techniques and tools used for software security. Students will study state-of-the-art vulnerability analysis techniques and tools. In particular, this class covers many static and dynamic analysis techniques, including program analysis, dynamic program instrumentation, fuzzing, taint analysis, symbolic execution, etc. Depending on how many credits the student takes for this class, the coursework will consist of: paper reading, paper presentation, paper reviewing, and labs to learn the tools.
Notes: static and dynamic analysis techniques, including program analysis, dynamic program instrumentation, fuzzing, taint analysis, symbolic execution, etc.
Instruction Mode: Remote: real time and recorded
Class #: 23864
Dates: 01/25/2021 - 05/07/2021
Days, Time: M, 12:50PM-2:55PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 6/30 (6/30 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 703SEM registration number 23864 calendar icon | Course Catalog: CSE 703SEM orange catalog icon
CSE 704 Applied NLP and Computational Social Science (Seminar)
Section: JOSE
Instructor: Kenneth Joseph
Description: This seminar course will focus on giving students a broad understanding of state-of-the-art methods in NLP and how they can be applied to address questions in the social sciences and/or humanities. Topics will also include other relevant areas of computational social science, broadly construed, including research on ethics, fairness, and power in applications of machine learning.
Prereqs: None, but previous experience with machine learning or advanced statistics is encouraged
URL: https://kennyjoseph.github.io/cse702
Instruction Mode: Remote: real time and recorded
Class #: 24673
Dates: 01/25/2021 - 05/07/2021
Days, Time: W, 10:25AM-12:30PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 6/30 (6/30 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 704SEM registration number 24673 calendar icon | Course Catalog: CSE 704SEM orange catalog icon
CSE 705 Privacy Preserving Machine Learning (Seminar)
Section: RATH
Instructor: Nalini Ratha
Description: Recent AI/ML systems have demonstrated unprecedented growth by exploiting deep neural networks for building solution for many complex problems. As these systems are deployed in many mission critical applications, they are expected to be secure, robust, trustworthy and privacy friendly. In the first part of the course, we will review the current approaches through papers published at top conferences. In the second part, we will dwell upon the open source tools available for these purposes.
Notes: Pattern recognition, Machine Learning, Deep Learning
Prereqs: Pattern recognition, Machine Learning, Deep Learning
Instruction Mode: Remote: real time and recorded
Class #: 24674
Dates: 01/25/2021 - 05/07/2021
Days, Time: R, 3:15PM-5:20PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 1/30 (1/30 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 705SEM registration number 24674 calendar icon | Course Catalog: CSE 705SEM orange catalog icon
CSE 706 Multilevel Solvers for Multiphysics Simulation (Seminar)
Section: KNEP
Instructor: Matthew Knepley
Description: We will design, build, test, and run simulators for interesting physical problems such as mantle dynamics, magnetohydrodynamics, and subsurface flow. Students will likely work in groups and can choose their own focus. The class will encourage students to make use of the PETSc libraries (http://www.mcs.anl.gov/petsc) and CCR.
Notes: Scalable Algebraic Solvers for Partial Differential Equations
Instruction Mode: Remote: real time and recorded
Class #: 18022
Dates: 01/25/2021 - 05/07/2021
Days, Time: T, 12:50PM-2:55PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 10/10 (10/10 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 706SEM registration number 18022 calendar icon | Course Catalog: CSE 706SEM orange catalog icon
CSE 713 Wireless Networks Security - Principles and Practices (Seminar)
Section: UPAD
Instructor: Shambhu Upadhyaya
Description: The seminar will start with a sweeping overview of Wireless Networking, Security issues in Wireless Networks and the Challenges, Threats and Hacking Methodologies. We will then cover Routing Security in Mobile Ad hoc Networks, Sensor Networks Security (Attacks and Countermeasures), Robust Localization in Sensor Networks, Security in Wireless Mesh Networks, Trust issues in MANETs, and QoS-Aware MAC Protocols and their security implications. We will also look into Vehicular Networks Security, Smart Grid Security and Security of Internet of Things (IoT), depending upon the student interests and time.
Notes: Overview of Security Issues in Wireless Networks, WEP Security, WPA and RSN, Security of MANETs, Security of Sensor Networks, Wireless Mesh Networks and Security, Trust in Wireless Networks, Vehicular Networks Security, Smart Grid Security and Security of Internet of Things (IoT)
Prereqs: A course on Computer Networks and basic knowledge of computer security. Some programming experience is essential.
Coreqs: None.
URL: https://cse.buffalo.edu/~shambhu/cse71321
Instruction Mode: Remote: real time and recorded
Class #: 22089
Dates: 01/25/2021 - 05/07/2021
Days, Time: T, 10:25AM-12:30PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 7/15 (7/15 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 713SEM registration number 22089 calendar icon | Course Catalog: CSE 713SEM orange catalog icon
CSE 715 Understanding Data for Explainable and Equitable Machine Learning (Seminar)
Section: A
Instructor: Oliver Kennedy
Description: Machine learning models are only as good as the data used to train them. Understanding the data is critical to creating unbiased models that make reliable predictions. In this class, we will read a range of papers that explore how data processing, preparation, and visualization techniques can be used to improve the quality of models.
Notes: An exploration of recent research on how data preparation, visualization, and processing techniques can be used to ensuring equitable outcomes from machine learning.
URL: https://odin.cse.buffalo.edu/teaching/cse-7xx/2021sp.html
Instruction Mode: Remote: real time and recorded
Class #: 24123
Dates: 01/25/2021 - 05/07/2021
Days, Time: M, 3:15PM-5:20PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 6/30 (6/30 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 715SEM registration number 24123 calendar icon | Course Catalog: CSE 715SEM orange catalog icon
CSE 730 Graph algorithms based on Graph Orientations and their Applications (Seminar)
Section: HE
Instructor: Roger He
Description: The seminar is research oriented in nature, focused on problems I have been working on in the past decade. We will discuss a number of open problems. Seminar Structure: I will present material during the first 1/2 to 2/3 of the classes. Students read papers and present selected papers during the remaining classes. Grading: S/U. Credits: 1-3
Notes: An "orientation" of an undirected graph G is an assignment of direction to the edges of G. We require orientation to satisfy certain conditions. These special orientations result in interesting combinatorial structures, which lead to elegant and efficient algorithms for solving certain problems in Graph theory, computational geometry, graph drawing. .
Prereqs: CSE 531, or permission of instructor
Instruction Mode: Remote: real time and recorded
Class #: 19475
Dates: 01/25/2021 - 05/07/2021
Days, Time: T, 10:25AM-12:30PM
Location: Remote
Credit Hours: 1.00-3.00
Enrollment: 3/20 (3/20 seats reserved for computer science & engineering majors only) (Active)
Links: Registration: CSE 730SEM registration number 19475 calendar icon | Course Catalog: CSE 730SEM orange catalog icon