MATRIX Spring Seminar Series – Dr. Ayse Coskun

AI for Efficient and Resilient Computing

Ayse Coskun

Boston University

 https://utsa.zoom.us/j/92387759081

Friday, February 4, 2022

11 AM – 12 PM CST

Today’s computers, ranging from small-scale embedded to large-scale systems, face challenges in delivering predictable performance, while maintaining efficiency, resilience, and security. Much of computer system management has traditionally relied on (manual) expert analysis and policies that rely on heuristics derived based on such analysis. This talk will demonstrate a new approach on designing “automated analytics” methods for computing systems, leading the path towards a longer-term vision where computing systems are able to self-manage and improve. Specifically, the talk will first cover how to systematically diagnose root causes of performance variations (or performance “anomalies”), which cause substantial efficiency losses and higher cost. Second, it will discuss how to identify applications running on computing systems and discuss how such discoveries can help reduce vulnerabilities and avoid unwanted applications. The talk will highlight how to apply machine learning to help understand and improve complex systems and show several pathways and challenges in real-world deployment of AI-based methods.

LINK

MATRIX Spring Seminar Series – Dr. Ethan Ahn

Hardware Implementation of Machine Learning by Emerging Nanodevices

Ethan C. Ahn

Assistant Professor of Electrical & Computer Engineering

The University of Texas at San Antonio

 https://utsa.zoom.us/j/92387759081

Friday, January 28, 2022

11 AM – 12 PM CST

The conventional scaling of today’s silicon-CMOS technology cannot satisfy the performance and energy-efficiency needs of abundant-data applications, as they require real-time analytics on enormous quantities of user data. Therefore, research is essential on novel computing hardware to tackle the fundamental limitation of the conventional von Neumann computing (“memory bottleneck”) and further enable emerging applications in e-commerce transactions, financial or business decisions, information security, defense, and forecasting of retail trends and demands. Neuromorphic (bio- or brain-inspired) computing is an emerging computing paradigm that takes inspiration from the way the brain computes. While computing systems based on the classical von Neumann architecture have one or more central processing units physically separated from memory, biological information processing features a co-localized memory and logic system where memory is distributed with the processing. Because the neural networks are extremely efficient at certain tasks that require massive amounts of data to be processed (e.g., recognition, classification, and prediction), research on neuromorphic computing is strongly driven by the need to invent a new computing topology that can lead to great improvements in computing efficiency in these machine learning tasks. In this talk, cutting-edge research on emerging nanoscale memory devices such as resistive random access memory (RRAM), phase-change memory (PCM), and spin-transfer-torque magnetic random access memory (STT-MRAM) is introduced in the context of hardware implementation of machine learning. Future perspectives on these emerging device technologies will also be discussed.

LINK

MATRIX Fall Seminar Series – Dr. Jignesh M. Patel

Conversational Citizen Data Science

Dr. Jignesh M. Patel

University of Wisconsin

Friday, November 5, 2021

11 AM – 12 PM CST

https://utsa.zoom.us/j/98953233499

Abstract: Today, enterprises rely on complex programs written by data scientists to extract meaningful insights from their data. That level of analytics is simply out of reach for most enterprise users. DataChat, as spin-out from U. Wisconsin, levels the playing field by allowing anyone and everyone in an organization to self-serve sophisticated data analysis. Users build data science pipelines by chatting with the platform in an accuracy-controlled subset of English. The platform then uses advanced AI techniques to translate the conversation into the appropriate data science functions and delivers the results in real time. This talk will describe the DataChat platform and present results from a user study.

SAVE THE DATE — MATRIX OPEN HOUSE

Please Save the Date for MATRIX AI Consortium Open House.

Date: 11/05/2021

Time: 3:00PM – 5:00PM CST

More details to come!

MATRIX Fall Seminar Series – Dr. Matei Ciocarlie

An Intelligent Mind for an Intelligent Hand: Sensor, Mechanism and Policy Design for Versatile Manipulators

Dr. Matei Ciocarlie

Columbia University

Friday, October 29, 2021

11 AM – 12 PM CST

https://utsa.zoom.us/j/98953233499

Abstract: What is the key to success in dexterous manipulation: the mechanical structure of the hand, the rich tactile and proprioceptive data it can collect, analysis and planning in the brain, or perhaps all of these? Believing these areas are deeply intertwined, we are pursuing them simultaneously. From a mechanism design perspective, I will present our work on optimizing the hand transmission hardware along with the grasping policy using joint optimization algorithms, an approach we refer to as “Hardware as Policy”. From a sensing perspective, I will present our optics-based tactile finger, providing accurate touch information over a multi-curved three-dimensional surface with no blind spots. Finally, from a motor learning perspective, I will talk about ongoing work on learning tactile-based policies for in-hand manipulation.

MATRIX Fall Seminar Series – Dr. Claire Walton

Control Theory and Deep Learning: Synergistic Partners in Theory and Applications

Dr. Claire Walton

University of Texas San Antonio

Friday, October 22, 2021

11 AM – 12 PM CST

https://utsa.zoom.us/j/98953233499

Abstract: Recent research has revealed significant connections between deep learning infrastructures such as neural networks and the modelling and control of complex dynamic systems.  Dynamic systems describe applications from self-driving cars to energy conservation to SpaceX rockets. Control of these systems brings up many challenges, such as nonlinearity, uncertainty, high dimensionality, and real-time decision-making demands. Application of neural nets to dynamic system control problems is an exciting current research area, which has already provided promising examples. However, perhaps a more surprising direction of impact has been the application of dynamic systems insights to deep learning itself. Equivalencies have been found between neural networks and the optimal control of dynamic systems, suggesting the computational tools of the latter can be used for the former. This has opened the door to many exciting possibilities driven by these equivalencies, such as the use of computational control algorithms to train neural networks, and development of network architectures developed from discretized control and dynamics models. This talk will provide a survey of these topics and of the cross-fertilization underway between control theory and deep learning.