Lecture Series Archive

FPGA Acceleration on Artificial Intelligence

Dr. Xiaokun Yang

Dr. Xiaokun Yang
University of Houston-Clear Lake, Houston, TX

Thu, 02/18/2021

Abstract – Hardware acceleration on Artificial Intelligence (AI) has become an indispensable technique for a wide range of real-time applications such as video classification, speech recognition, and autonomous robot. Specifically in the era of edge computing, to limit the complexity of AI algorithms in the power-constrained and latency-critical scenarios is a big challenge. Therefore, this presentation focuses on mapping neural networks onto field-programmable gate array (FPGA) with the benefits of high parallelism and programmability. Generally, two research subjects are discussed: the design and evaluation to FPGA acceleration and system-on-chip (SoC) architecture to FPGA. First, case studies to the design on FPGA accelerator are presented, including handwritten digit recognition and real-time music transcription. Second, a low-cost and energy-efficient SoC architecture is discussed to the applications of edge devices. By integrating DMA, AES core, bus wrappers, and open verification components (OVCs), a UVM-based environment is finally established to verify the functionality of the SoC.

Dr. Xiaokun Yang received his Ph.D. from the Department of Electrical and Computer Engineering (ECE), Florida International University (FIU), USA in Spring 2016. He is currently an Assistant Professor at the College of Science and Engineering, University of Houston-Clear Lake. From 2007 to 2012, he has also worked as a Senior ASIC Design and Verification Engineer at Advanced Micro Devices (AMD) and China Electronic Corporation (CEC). His research interests include Hardware Acceleration on AI/ML, ASIC/FPGA Design and Verification on Neural Networks, and Energy-Efficiency System-on-Chip (SoC) Architecture. As the first author or corresponding author, Dr. Yang has published more than 50 papers including 3 patents, more than 15 peer-review journals, and more than 30 prestigious international conferences. He has served on several editorial boards and journal reviewers including IEEE Trans. on Computer, IEEE Trans. on VLSI, and IEEE Trans. on Education, and numerous conference committees including ISVLSI and ISQED.

Security of Networked Control Systems

Dr. Arman Sargolzaei

Dr. Arman Sargolzaei
Assistant Professor
ME Department, Tennessee Technological University, Cookeville, TE

Thu, 02/04/2021

Abstract – With the immense growth of networked control systems (NCSs) development and utilization in critical infrastructures such as unmanned aerial vehicles and autonomous systems, assurance of their safety, security, and resiliency are yet a significant challenge for industries. Although defense mechanisms for NCSs have been significantly improved, incorporating smart detection and control platforms, yet a similar growth in the generations and models of cyber-attacks cannot be discarded. Existing control and communication protocol strategies are not fully capable of preventing and responding to new types of cyber-attacks. This requires vulnerability identifications along with smart, collaborative integration of controllers, sensors, actuators, and communication protocols in real-time. The seminar discusses recently introduced a mathematical approach to the Time Delay Switch (TDS) attack as a comprehensive outlook for the new generation of cyber-attacks.

Dr. Arman Sargolzaei's expertise is in applying linear and nonlinear control methods, machine learning, and artificial intelligence to the field of Cyber-Physical Systems. His mission is to enhance the quality of life for people, by assuring the safety, security, and privacy concerns through extensive collaboration among multi-disciplinary fields. His research on the security of Networked Control Systems (NCSs) and resiliency of Multi-agent systems, particularly his doctoral dissertations combined with the knowledge of control theory, system identification, mathematics, and statistics carried significant practical implications in better understanding the pathways of faults, failure, and attack detection and compensation for NCSs. He is recognized with the honor of the "Faculty Research Excellence Award" for two consecutive years. He is currently an Assistant Professor of Mechanical Engineering at Tennessee Technological University. Before joining Tennessee Tech, he was director of Advanced Mobility Institute (AMI) and an Assistant Professor of Electrical Engineering at Florida Polytechnic University.

Probabilistic and Approximate Computation in Software and Hardware Models

Bala Ravikumar

Professor Bala Ravikumar
Professor, Chair
Department of Computer Science, SSU, Rohnert Park, CA

Thu, 11/19/2020

Abstract - Everyone knows that modern digital computers are based on deterministic Boolean logic gates that are assumed to perform exact computation of logical operations such as AND, NOT etc. In this talk, we will explore two alternatives to this framework in which the demand on the output being correct on all inputs is relaxed. First, we will consider a state machine model as a way to approximate the solutions of some computational problems. The second one is a stochastic model of logic gates that provides an alternative hardware basis for building digital computers. Some applications of these models will also be presented.

Dr. Ravikumar received his Ph.D. in Computer Science from the University of Minnesota and has taught at many universities including University of Minnesota, University of Rhode Island, San Francisco State University and Sonoma State University. He has supervised many graduate and undergraduate projects. He is an editor of the International Journal of the Foundations of Computer Science and has served on the program committees of many international conferences. He has presented invited and contributed talks in more than fifty international conferences.

Towards Hardware Cybersecurity

Houman Homayoun

Professor Houman Homayoun
Associate Professor
Dept. of ECE, UC Davis, Davis, CA

Thu, 11/05/2020

Abstract - Electronic system security, trust and reliability has become an increasingly critical area of concern for modern society. Secure hardware systems, platforms, as well as supply chains are critical to industry and government sectors such as national defense, healthcare, transportation, and financial. Traditionally, authenticity and integrity of data has been protected with various security protocol at the software level with the underlying hardware assumed to be secure, and reliable. This assumption however is no longer true with an increasing number of attacks reported on the hardware.

In this talk I will address the security and vulnerability challenges in the horizontal integrated hardware development process. I will then present the concept of logic obfuscation through using hybrid spin-transfer torque CMOS look up tables which is our latest effort on developing a cost-effective solution to prevent physical reverse engineering attacks.

Dr. Houman Homayoun is an Associate Professor in the Department of Electrical and Computer Engineering (ECE) at UC-Davis. He is also the director of National Science Foundation Center for Hardware and Embedded Systems Security and Trust (CHEST). Houman conducts research in hardware security and trust, data-intensive computing and heterogeneous computing, where he has published more than 100 technical papers and directed over $8M in research funding from NSF, DARPA, AFRL, NIST and various industrial sponsors. He received several best paper awards and nominations in various conferences including GLSVLSI 2016, ICDM 2019, and ICCAD 2019, and 2020. He served as Member of Advisory Committee, Cybersecurity Research and Technology Commercialization in the Commonwealth of Virginia in 2018. Since 2017 he has been serving as an Associate Editor of IEEE Transactions on VLSI. He was the technical program co-chair of GLSVLSI 2018 and the general chair of 2019 conference.

Supply Chain - New Product Introduction Process

Pelin Mohamed

Dr. Pelin Salem
Senior Test Development Engineer
Cisco, San Jose, CA

Thu, 10/15/2020

Abstract - Cisco is the worldwide leader in networking and is transforming how people connect, communicate, and collaborate. Supply Chain Operations is a key enabler of Cisco’s success which is mainly due to cross-functional Supply Chain Operations teams that manage the relationships between suppliers and contract manufacturers towards building the products its customers need. In short, Supply Chain Operations is what connects suppliers and customers. Supply Chain Operations is responsible for accelerating innovation, enabling profitable growth while establishing sustainability, and delivering excellence in customer experience. Supply Chain Operations spans the entire product lifecycle with accountability for new product introduction, sourcing, and supplier management, planning, manufacturing, logistics, and quality. This talk gives a brief overview of the phases in Cisco’s supply chain flow and defines the roles and responsibilities at each stage.

Dr. Pelin Salem received her BSc. Degree in Electrical-Electronics Engineering from Blacksea Technical University (KTU) in Trabzon, Turkey in 2005, her MSc in Electrical Engineering from New Jersey Institute of Technology (NJIT) in New Jersey, USA in 2009, her MSc in Bioscience from King Abdullah University of Science and Technology (KAUST) in Thuwal, Saudi Arabia in 2011, and her PhD in Electrical Engineering from NJIT in 2018. She has worked in defense industry designing automated test systems for NATO Avionics and F16 fighter jet Electronic Warfare Systems between 2005-2009, in academia as a researcher and an educator between 2009-2016 in the US, KSA, and China, and in manufacturing industry since 2016. She has been with Cisco Systems as a Senior Test Development Engineer in Internet of Things Business Unit, working on Industrial IOT New Product Introduction since January 2019.

Pages