2022 Lunch & Learns

Visible to the public 

2 0 2 2 L U N C H & L E A R N S E R I E S

This summer our 2022 VU-ISIS interns will have the opportunity to "lunch & learn" with a handful of graduate (and graduated) students and researchers from our department. The experience will be an intimate and informal one, providing the time for important networking, learning, and career building insight each student can carry with them into future opportunities.


2022 SCHEDULE

Thursday, May 26: David Wang

Hanchen David Wang is a second-year Ph.D. student at Vanderbilt specializing in Computer Science and therapeutic healthcare. He is currently working with his advisor, Meiyi Ma, as a research assistant at the Institute for Software Integrated Systems on research regarding the quality of exercises. David received his bachelor of science at the University of California, Irvine. He loves weightlifting and swimming in his free time. Please feel free to reach out to him to let him know if you have any questions.

Thursday, June 2: Shreyas Ramakrishna

Shreyas Ramakrishna is a 5th year PhD student in the Department of Electrical Engineering and Computer Science and is working as a research assistant with Prof. Abhishek Dubey at the Institute for Software Integrated Systems. He received his M.S. degree in Electrical Engineering from Technical University Kaiserslautern (Germany) in June 2015 and completed his undergraduate studies in Electrical engineering from Visvesvaraya Technological University, India in 2012.

He is currently working on the Assured Autonomy project.

Thursday, June 9: Patrick Musau

Patrick Musau is an Electrical Engineering (EE) PhD student at Vanderbilt University. He joined the VeriVITAL research group in the Summer of 2017 under Dr. Taylor T. Johnson. Patrick's research work focuses primarily in the use of verification techniques and software tools to foster the creation of intelligent autonomous Cyber-Physical Systems (CPS) with Learning-Enabled Components (LEC). Patrick has been part of the DARPA Assured Autonomy project for the last two years, where he has been working with unmanned underwater vehicles (in simulation), and an autonomous vehicle platform named the F1Tenth (simulation and hardware). He has also been involved in the development of the Neural Network Verification (NNV) toolbox that makes use of reachability analysis techniques to reason about the behavior of a variety of neural network architectures. Patrick, enjoys working with autonomous drones and cars, and over the last couple of years, he has been a member of two Vanderbilt teams that have competed in the F1/10 autonomous racing competitions (2019 CPS-IoT Week and 2019 Embedded Systems week) and at the 2019 NSF CPS Drone Challenge.

Thursday, June 16: Akhilesh Raj (recording found here)

Akhilesh is currently pursuing his PhD in the Department of Electrical Engineering at Vanderbilt University. He is a Teaching Assistant under the graduate engineering fellowship program advised by Dr. Aniruddha Gokhale, at the Institute for Software Integrated Systems. His Ph.D. focuses on composition of surrogate models. Akhilesh's primary research area is in control systems design and engineering with applications to various industrial applications. He also considers the application of Reinforcement Learning as one of the possible replacements for various control applications and theories while considering the optimality of the information that are being used for training the RL models.

On June 16th, Akhilesh will be presenting his ongoing research on composition of surrogate models, which are reduced order models depicting any natural processes. Through his research he aims at developing a new training method for these models while deploying it as a part of any large-scale complex process, provided certain conditions are satisfied. It will be an interesting topic for researchers working on machine learning models, filtering techniques, observers, surrogate modeling etc. Akhilesh will only be presenting the higher level picture of his research so that it will be inclusive.

Thursday, June 23 (9:30 a.m.): Diego Manzanas Lopez

PhD Dissertation Defense: Learning and Verification of Dynamical System with Neural Network Components

Abstract
Cyber-physical systems (CPSs) with learning-enable components (LECs) are becoming very popular, especially in the area of autonomous vehicles such as unmanned aircraft, autonomous and partially autonomous cars, and underwater vehicles. However, before they can be widely adopted in these safety-critical applications, we need to ensure their design and operation are correct and safe. The main challenges to verify their behavior include the formal modelling of the dynamics defining the interaction of the CPS with the real world, and the lack of transparency on the internal operation of the LECs. The following dissertation presents approaches to both challenges and case studies to evaluate the performance of our techniques. We present a novel method for learning the behavior of dynamical systems that present both continuous and discrete dynamics with the use of a hybrid automata learning framework with nonlinear dynamics. We also present case studies on the verification of autonomous CPS with LECs, more specifically with feedforward neural network controllers. Finally, we present a formal verification framework for a recently introduced deep learning architecture that can be utilized both as a part of a control system and as a dynamical model, named neural ordinary differential equations (neural ODEs). We extend its definition to provide a general class of neural ODEs, and evaluate our verification framework on several benchmarks in the area of dynamical systems, control systems and image recognition.

Thursday, June 30: cancelled

Thursday, July 7: Robert Canady

Robert Canady is a PhD student in the Department of Electrical and Computer Engineering. He joined the Distributed Object Computing (DOC) group under Dr. Aniruddha Gokhale in the summer of 2017 at the Institute for Software Integrated Systems. Robert has switched between being a teaching and research assistant under different projects. He is currently interning at the Autonomy Technology Research Center out of Wright State University. Robert's research is at the intersection of Edge Computing and Adversarial Machine Learning, where he is looking into ways to make machine learning models deployed at the edge more efficient while also being robust to unseen data/conditions or malicious attacks. He received his BA in Mathematics and Physics from Transylvania University in 2017.

Thursday, July 14: Tim Darrah

Timothy Darrah graduated magna cumme laude from Tennessee State University with a bachelor's of science in computer science in 2017 prior to entering the PhD program here at Vanderbilt University. His focus is on extending the current state-of-the-art in health management technologies for cyber physical systems to include system-level prognostics, predictive maintenance, and decision making. He spent the summer of 2019 as an intern at NASA Ames Research Center, developing a system-level prognostics framework for UAV powertrain systems as well as constructing a hardware-in-the-loop testbed. He was recently awarded a prestigious NASA Fellowship which will support his PhD thesis research on resource-constrained decision making under uncertainty. Previously he worked on a Navy STTR project developing a more advanced health management system for the Navy's fleet of combatant crafts. Timothy served 7 years in the U.S. Army as an airborne infantryman and later as an avionics maintenance technician. He was deployed to Afghanistan in 2011, has received numerous awards for conduct and achievements, held the rank of staff sergeant, and was honorably discharged in 2013.

Thursday, July 21: Matt Nice

Matt Nice is a PhD student in Civil Engineering and the Insitute for Software Integrated Systems at Vanderbilt University. He earned his M.Eng in Cyber-Physical Systems at Vanderbilt University. He earned his B.S.E. at Tulane University. His research interests are broadly in transportation cyber-physical systems. That includes autonomous vehicles, sensor networks, and human-in-the-loop systems. He is focused on empirical successes from research ideas.