Spring Seminar Series 2024 – Dr. Yimin D. Zhang

Sparse Sensor Array Processing for High-Resolution Sensing

Yimin D. Zhang, Ph.D.
Associate Professor
Department of Electrical and Computer Engineering
Temple University, Philadelphia, PA
IEEE Fellow, SPIE Fellow, IEEE SPS Distinguished Lecturer
http://yiminzhang.com

2/2/2024
11am – 12pm CST
Location: San Pedro 1, Yotta Room 430
506 Dolorosa St, San Antonio, TX 78204

Organizers and Sponsors:
UTSA MATRIX AI Consortium; UTSA Department of ECE; IEEE Signal Processing Society (Distinguished Lecturer Program); IEEE Lone Star Section, Joint Communications and Signal Processing Chapter

Abstract:
Array signal processing plays a crucial role in various applications, including radar sensing, wireless communications, and medical imaging. It serves as a vital technology for tasks like directional beamforming, interference suppression, multiuser access, direction finding, signal localization, and computational imaging. The evolving needs of modern radar sensing and wireless communications demand higher spatial resolution and improved estimation accuracy. However, these requirements often translate into a significant hardware cost due to the large array aperture and the high number of array sensors.To address these challenges, sparse sensor array design and processing offer low-complexity solutions that enhance sensing capability and improve performance with a reduced number of array sensors. This presentation explores recent advancements in concepts, design strategies, and processing methods for sparse array-based sensing, aiming to achieve high spatial resolution and an increased number of degrees of freedom. These advancements leverage recent progress in compressive sensing, optimization, and machine learning. Various sparse array processing techniques will be discussed and array designs that reduce difference lag redundancies and exploit frequency diversity will be presented, providing insights into efficient and cost-effective solutions for array signal processing in diverse applications.

Spring Seminar Series 2024 – Dr. Wenpin Tang

Contractive Diffusion Models and Score Matching by Continuous Reinforcement Learning

Wenpin Tang, Ph.D.
Assistant Professor
Department of Industrial Engineering and Operations Research
Columbia University, New York, NY
https://www.columbia.edu/~wt2319

01/26/2024
11am – 12pm CST
Location: San Pedro 1, Yotta Room 430
506 Dolorosa St, San Antonio, TX 78204
Zoom: https://utsa.zoom.us/j/94807623288

Abstract:
In this talk, I will link two different topics. The past decade has witnessed the success of generative modeling (e.g., GANs and VAEs) in creating high quality samples in a wide variety of data modalities. The first part of this talk is concerned with the recently developed diffusion models, the key idea of which is to reverse a certain stochastic dynamics. I will first take a continuous-time perspective and examine the performance of different SDE schemes including VE (variance exploding) and VP (variance preserving). The discretization is more subtle, and our idea is to “contract” the reversed dynamics leading to possible new diffusion model designs. In the second part, I will talk about continuous reinforcement learning. Reinforcement Learning (RL) has been successfully applied to wide-ranging domains in the past decade. In recent years, a fast-growing body of research has extended the frontiers of continuous RL to designing model-free methods and algorithms. I will discuss the recently introduced “q-learning” and closely related policy optimization. Finally, I will highlight a natural application of continuous RL to fine-tune the score function in the diffusion models.

Fall Seminar Series 2023 – Dr. Debashis Sahoo

Data Science for Translational Research

Dr. Debashis Sahoo, PhD

Associate Professor

Pediatrics and Computer Science and Engineering

University of California San Diego

11/17/2023

11AM – 12PM CST

Location: UTSA Main Campus, Student Union Hidalgo Room (2.214)

Zoom: https://utsa.zoom.us/j/91049981814

Translational research aims to swiftly apply basic science discoveries in practical healthcare. Productivity hurdles can impede the quick translation of research into healthcare breakthroughs, with issues like reproducibility and generalizability of biological results in clinical settings posing significant challenges. Concerns about irreproducible results are on the rise, with over 70% of researchers reportedly facing challenges reproducing others’ experiments, and more than half struggling with their own. Drug development, a crucial facet of translational research, maintains a low success rate despite past efforts.

Part of the problem lies in the tools of data science and statistics used. I’ll introduce you to a new approach—Boolean analysis of large and diverse biological datasets. In my research group, we’ve pioneered this method and developed computational tools to uncover invariant logical relationships between genes. Join me as we explore how leveraging these invariant relationships can enhance the reproducibility of current approaches. We will discuss how Boolean analysis can transform the power of AI/ML approaches.

Fall Seminar Series 2023 – Dr. Srikanth Saripalli

Autonomy in the Wild: Good, Bad and the Ugly

Dr. Srikanth Saripalli

 Professor in Department of Mechanical Engineering, Director for Center for Autonomous Vehicles and Sensor Systems (CANVASS)

Texas A&M University

11/10/2023

11AM – 12PM CST

Location: UTSA San Pedro 1, Yotta Room 430

Zoom: https://utsa.zoom.us/j/91049981814

UxVs (Unmanned Aerial/Ground/Surface/Underwater Vehicles) are expected to expand their applications to several civilian domains such as Autonomous Driving, precision agriculture, infrastructure monitoring & disaster response. However for these UxVs to perform these tasks with full autonomy they must satisfy multiple requirements: 1) Navigate in GPS-denied Environments 2) Sense and Avoid Obstacles 3) Able to determine interesting phenomenon. In this talk, I will give an overview of our algorithms on combining vision with Inertial Measurement Unit and GPS for accurate state estimation of the vehicle. I will describe our algorithms for mapping using thermal, visual and LIDAR sensors that enable autonomous navigation in various challenging conditions.  A major portion of the talk will be on applications of the above algorithms to real vehicles (aerial, ground) and the lessons that we have learned i.e. what worked and what didn’t and how we should go about building such systems.

Fall Seminar Series 2023 *Distinguished Speaker* Dr. David Pan of UT Austin

Closing the Virtuous Cycle of Photonics for AI and AI for Photonics

Dr. David Z. Pan

Department of Electrical and Computer Engineering

The University of Texas at Austin

11/3/2023

11AM – 12PM CST

Location: UTSA Main Campus, Student Union Hidalgo Room (2.214)

Zoom: https://utsa.zoom.us/j/91049981814

Photonics is a promising emerging technology that offers huge performance and efficiency benefits for AI/ML computing. There has been increasing interest in developing photonic AI accelerators for the next generation datacenters, smart sensing, intelligent edge, and automotive computing. However, realizing its full potential requires overcoming significant design challenges through a cross-layer co-design approach, where devices, circuits, architectures, and algorithms are optimized together. In this talk, I will show how photonics and AI interplay with each other. On the front of Photonics for AI, I will show some case studies of customized photonic device, circuit, architecture, and software co-design for efficient machine learning. On the front of AI for Photonics, I will show a novel machine learning framework for real-time photonic device simulations, which has the potential to speed up the customized photonic structure design through AI-enhanced optimizations. Closing the virtuous cycle of photonics for AI and AI for photonics shall hold great potential to significantly advance the state-of-the-art of each other.

Fall Seminar Series 2023 *In-Person Event* – Dr. Christopher Kanan

Efficient Continual Deep Learning

Dr. Christopher Kanan

University of Rochester

10/27/2023

11AM – 12PM CST

Location: SAN PEDRO 1 YOTTA ROOM 430

506 Dolorosa St, San Antonio, TX 78204

Zoom: https://utsa.zoom.us/j/91049981814

Continual learning methods enable progressive knowledge accumulation in deep neural networks, and it has the potential to make training much more efficient and has many exciting applications such as on-device learning. Whereas conventional deep learning can suffer from catastrophic forgetting of previously acquired abilities when updating a network, over the past five years, continual learning has largely overcome this limitation. Despite this achievement, I argue the vast majority of continual learning algorithms have little practical value. In this talk, I show that methods are highly inefficient in terms of compute, memory, and storage. Some methods even require more computation than re-training from scratch as a dataset grows! For continual learning to have real-world applicability, the research community cannot ignore the resources used by these algorithms. Subsequently, I demonstrate that three new neuroscience-inspired algorithms created by my lab can vastly improve computational efficiency on large-scale vision and text understanding datasets. Our work has the potential to make continual learning more practical and widely adopted as well as advancing the goals of GreenAI.