Each year the Department of Computer Science and Engineering invites prominent computer scientists and computer engineers to visit Texas A&M and speak about their research. This distinguished lecture series is sponsored by academia and industry.
2022-2023 Distinguished Lecture Series
March 2023
6 - Monday - 4:10 p.m.
Learning to Generalize to Out-of-Distribution Data
Dr. Jiebo Luo, Professor, University of Rochester
Abstract
Data-driven deep models will inherit the characteristics of the training data and thus can handle the in-distribution testing data well. However, in real-life applications, the distribution of testing data is likely different from that of training data because of many factors, including distribution shift, domain shift, isolated data server, noisy labels, and so on. Such challenging datasets may make the learned model unreliable and pose threats to the learned model's generalization capacity for unseen testing data. This talk will cover several related research topics. First, real-world data inevitably contains noise and bias. We adopt adversarial learning to obtain bias/domain invariant features so that the learned model can generalize to out-of-distribution testing data. Second, due to privacy concerns and transmission load, directly transferring data from edge devices to a centralized server to train a unified model is usually infeasible, while the data are often heterogeneously distributed among different insolated edge devices. We propose federated learning methods to alleviate the problem with applications in molecular graphs, medical images, and time series data.
Biography
Jiebo Luo is the Albert Arendt Hopeman Professor of Engineering and professor of computer science at the University of Rochester. His research focuses on computer vision, natural language processing, machine learning, data mining, social media, computational social science, and digital health. Luo has authored nearly 600 papers and over 90 U.S. patents. He is also an active member of the research community: a fellow of NAI, Association for Computing Machinery (ACM), Association for the Advancement of Artificial Intelligence (AAAI), Institute of Electrical and Electronics Engineers (IEEE), International Association for Pattern Recognition, SPIE, editor-in-chief of the IEEE Transactions on Multimedia (2020-2022), as well as a member of the editorial boards of the IEEE Transactions on Pattern Analysis and Machine Intelligence (2006-2011), IEEE Transactions on Multimedia (2004-2009, 2013-2016), IEEE Transactions on Circuits and Systems for Video Technology (2010-2012), IEEE Transactions on Big Data (2018-present), Pattern Recognition (2002-2020), ACM Transactions on Intelligent Systems and Technology (2015-present) and so on. In addition, Luo served as an organizing or program committee member for numerous technical conferences sponsored by IEEE, ACM, AAAI, ACL, IAPR and SPIE, including, most notably, program co-chair of the 2010 ACM Multimedia Conference, 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 ACM Conference on Multimedia Retrieval and 2017 IEEE International Conference on Image Processing.
Faculty Contact: Tianbao Yang
20 - Monday - 4:10 p.m.
Human-in-the-Loop Creative AI
Dr. Takeo Igarashi, Professor, The University of Tokyo
Abstract
Generative models that apply deep learning to the generation of contents such as images and sound are attracting attention. However, generative process using deep learning is a black box, which makes it difficult for humans to understand and control. In this talk, I will introduce methods for human intervention and control of such generative processes and other computer-assisted content generation systems. I will show examples in computer-aided design using physical simulation, generative models of images, 3D models and acoustic signals.
Biography
Takeo Igarashi is a professor in the Department of Creative Informatics at The University of Tokyo. His research interests are in user interfaces and interactive computer graphics. Igarashi has received several awards, including the Association for Computing Machinery's (ACM) SIGGRAPH 2006 Significant New Researcher Award, the ACM CHI Academy award 2018 and the Asia Graphics 2020 Outstanding Technical Contributions Award. He served as a program co-chair for the ACM Symposium on User Interface Software and Technology (UIST) in 2013, a conference co-chair for ACM UIST in 2016, technical papers chair for SIGGRAPH ASIA in 2018 and technical program co-chair for ACM CHI in 2021.
Faculty Contact: Jeeeun Kim
April 2023
10 - Monday - 4:10 p.m.
The Many Dimensions of "Identity"
Dr. Radia Perlman, Computer Programmer and Network Engineer
Abstract
People usually assume that “the identity problem” is well-understood and that, given how long Internet authentication has been deployed, the world must have solved how to do that (whatever “that” is) securely. This talk describes various issues, for instance: how does a website get a name, how does a website get a certificate, how does a browser know what to trust to sign certificates, how a human finds a website, how a human acquires a name, and how a user proves they own their name. Surprisingly, there are issues with all of these aspects as deployed today. As with most security problems, some people propose “blockchain” as being “the solution.” This talk will describe what aspects of identity and authentication blockchain might address and compare a “blockchain” approach with what is deployed today. If the talk spurs spirited debate, all the better.
Biography
Dr. Radia Perlman will begin her association with Texas A&M University in September as a Hagler Fellow and will teach a network security class in the fall of 2023. Her specialties include network routing protocols and network security. Perlman developed the technology for making network routing self-stabilizing, largely self-managing, and scalable. She also invented the spanning tree algorithm, which transformed Ethernet from a technology that supported a few hundred nodes within a single building to something that could support large networks. Perlman also has made contributions in network security, including scalable data expiration, distributed algorithms despite malicious participants, distributed denial-of-service prevention techniques and user authentication. She is the author of the textbook “Interconnections” (about network layers two and three) and coauthor of “Network Security: Private Communication in a Public World” (about cryptography, quantum computing, quantum-safe public key algorithms and more). She holds an S.B. and S.M. in mathematics and a Ph.D. in computer science, all from the Massachusetts Institute of Technology.
Faculty Contact: Scott Schaefer
2020-2021 Distinguished Lecture Series
February 2021
22 - Monday - 1:20 p.m. (via Zoom)
PCI Express® 6.0: a low latency, high bandwidth, high reliability and cost-effective interconnect with 64.0 GT/s PAM-4 signaling
Dr. Debendra Das Sharma, fellow and director of the I/O Technology and Standards Group Intel Corporation
Abstract
PCI Express® (PCIe®¬) specification has been doubling the data rate every generation in a backwards compatible manner every two to three years. PCIe 6.0 specification will adopt PAM-4 signaling at 64.0 GT/s for maintaining the same channel reach of prior generations. A forward error correction (FEC) mechanism will offset the high BER of PAM-4. We propose a new flit-based approach with a light-weight, low-latency FEC coupled with a strong CRC and a low-latency link level retry mechanism to meet the stringent low-latency, high bandwidth and high reliability goals. Shared credit pooling across multiple virtual channels will be deployed to reduce the area and power overhead while providing the necessary quality of service guarantees. We also present a new low-power state that ensures power consumption is proportional to bandwidth usage without impacting the traffic flow.
Biography
Dr. Debendra Das Sharma is an Intel fellow in the Data Platforms Group and director of the I/O Technology and Standards Group at Intel Corporation. He is a leading expert on I/O subsystem and interface architecture. Das Sharma’s team delivers Intel-wide critical interconnect technologies in peripheral component interconnect express (PCIe), compute express link (CXL), Intel’s coherency interconnect and multichip package interconnect. He is a key driver of external standards for PCIe and CXL, and internal proprietary interfaces, as well as implementation.
Das Sharma joined Intel in 2001 as a technical lead in the Advanced Components Division, designing server chipsets. He previously worked with Hewlett-Packard, where he led development of their server chipsets. He holds 123 U.S. patents and is a frequent speaker and panelist at the PCI-SIG Developers Conference, CXL consortium events, Open Server Summit, Open Fabrics Alliance, Flash Memory Summit and Intel Developer Forum.
Das Sharma is a member of the Board of Directors for the PCI Special Interest Group (PCI-SIG) and a lead contributor to PCIe specifications since its inception. He is a co-inventor and founding member of the CXL consortium and co-leads the CXL Technical Task Force.
Das Sharma has a bachelor’s in technology (with honors) degree in computer science and engineering from the Indian Institute of Technology, Kharagpur, and a Ph.D. in computer engineering from the University of Massachusetts Amherst. He has also been awarded the Distinguished Alumnus Award from Indian Institute of Technology, Kharagpur.
Faculty Contact: Rabi Mahapatra
2019-2020 Distinguished Lecture Series
November 2019
4 - Monday - 4:10 p.m. (HRBB 124)
Human Behavioral Machine Intelligence from Multimodal Data
Shrikanth (Shri) Narayanan, University of Southern California, Los Angeles, CA
Open reception in the atrium outside room 124, immediately following Narayanan's presentation.
Faculty Contact: Theodora Chaspari
18 - Monday - 4:10 p.m. (HRBB 124)
Bias on the Website
Ricardo Baeza-Yates, NTENT & Northeastern University at Silicon Valley
Open reception in the atrium outside room 124, immediately following Baeza-Yates' presentation.
Faculty Contact: Juan Garay
2018-2019 Distinguished Lecture Series
September 2018
10 - Monday - 4:10 p.m. (HRBB 124)
End-to-end perceptual video streaming quality
Al Bovik,
Open reception in the atrium outside room 124, immediately following Bovik's presentation.
Faculty Contact: Atlas Wang
28 - Friday - 4:10 p.m. (ZACH Chevron Room)
Fun research in computer vision and robotics
Takeo Kanade, Carnegie Mellon University
Open reception in the Conoco Phillips Atrium (2nd floor, between Chevron Room and Starbucks) immediately following Kanade's presentation.
Faculty Contact: Dezhen Song and Nancy Amato
October 2018
3 - Wednesday - 4:10 p.m. (HRBB 124)
Cloud security
Rafail Ostrovsky, UCLA
Open reception in the atrium outside room 124, immediately following Ostrovsky's presentation.
Faculty Contact: Juan Garay
November 2018
28 - Wednesday - 4:10 p.m. (HRBB 124)
The Blocks World Redux
Martha Palmer, University of Colorado Boulder
Open reception in the atrium outside room 124, immediately following Palmer's presentation.
Faculty Contact: Ruihong Huang
December 2018
3 - Monday - 4:10 p.m. (HRBB 124)
Using technology for health and wellbeing
Mary Czerwinski, Visualization and Interaction (VIBE) Research Group
Open reception in the atrium outside room 124, immediately following Czerwinski's presentation.
Faculty Contact: Theodora Chaspari
2017-2018 Distinguished Lecture Series
2017-2018 Distinguished Lecture Abstracts
January 2018
29 Monday - 4:10pm (Room 124 HRBB)
Nikos Papanikolopoulos, University of Minnesota
Open reception in the atrium outside room 124, immediately following Papanikolopoulos' presentation.
Faculty Contact: Nancy M. Amato
Febuary 2018
19 - Monday - 4:10pm (Room 124 HRBB)
Aidong Zhang, University at Buffalo
Open reception in the atrium outside room 124, immediately following Zhang's presentation.
Faculty Contact: Xia (Ben) Hu
2016-2017 Distinguished Lecture Series
2016-2017 Distinguished Lecture Abstracts
January 2017
25 Wednesday -
Haesun Park, Georgia Institute of Technology
Open reception in the atrium outside room 124, immediately following Park's presentation.
Faculty Contact: Nick Duffield
30 - Monday - 4:10pm (Room 124 HRBB)
Vipin Kumar, University of Minnesota
Open reception in the atrium outside room 124, immediately following Kumar's presentation.
Faculty Contact: Nick Duffield
February 2017
8 Wednesday -
Charles Leiserson, Massachusetts Institute of Technology
Open reception in the atrium outside room 124, immediately following Dr. Leiserson's presentation.
Faculty Contact: Lawrence Rauchwerger
13 Monday - 4:10pm (Room 124 HRBB)
Tom Ball, Microsoft Research
Open reception in the atrium outside room 124, immediately following Ball's presentation.
Faculty Contact: Jeff Huang
April 2017
17 - Monday - 4:10pm (Room 124 HRBB)
Zoran Obradovic, Temple UniversityOpen reception in the atrium outside room 124, immediately following Obradovic's presentation.
Faculty Contact: Nick Duffield
December 2016
6 Tuesday -
The Texas A&M Cybersecurity Distinguished Lecture Series
Michael Reiter,
Faculty Contact: Riccardo Bettati
7 Wednesday -
Nikos Papanikolopoulos, University of Minnesota
Open reception in the atrium outside room 124, immediately following Papanikolopoulos' presentation.
Faculty Contact: Nancy M. Amato
2015-2016 Distinguished Lecture Series
2015-2016 Distinguished Lecture Abstracts