Towards Efficient Learning on Edge by Hyperdimensional Computing
9th Lecture of IEEE CS San Diego's 2025 Invited Seminar Series (Virtual)
Recent advancements in machine learning, while powerful, are often burdened by significant computational and memory requirements, limiting their deployment in resource-constrained settings. Hyper dimensional Computing (HDC) emerges as an alternative with its simplicity, lightweight operations, and robustness to errors. By encoding data into high-dimensional vectors and performing efficient algebraic computations, HDC opens a new avenue as an efficient learning paradigm. In this talk, Dr. Fatemeh Asgarinejad will introduce the fundamentals of HDC and briefly discuss existing research that has extensively explored various stages of HDC algorithm. Then, she will present three key domains of her research: First, she will discuss PIONEER, a novel approach that employs learned projection vectors to optimize the encoding process. By leveraging neural networks to learn these vectors, PIONEER enables HDC to achieve high accuracy with significant computational efficiency. Second, she will present HDXpose, an adversarial attack framework that exploits an advantage of HDC: “explainability”. By strategically analyzing and perturbing influential input points, HDXpose effectively unveils vulnerabilities within HDC models, underscoring the need for robust security measures in HDC system design. Lastly, Dr. Asgarinejad will show an application of HDC in developing a cost-effective and noise-resilient pressure mat system for human activity recognition. The HDC-based system surpasses CNNs in accuracy and efficiency.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- Contact Event Hosts
- Co-sponsored by Media Partner: Open Research Institute (ORI)
- Starts 12 August 2025 07:00 AM UTC
- Ends 27 August 2025 01:00 AM UTC
- No Admission Charge
Speakers
Fatemeh Asgarinejad of University of California, San Diego; University of California, Riverside
Towards Efficient Learning on Edge by Hyperdimensional Computing
Biography:
Fatemeh Asgarinejad is an incoming Assistant Professor of Teaching in the Electrical and Computer Engineering Department at the University of California, Riverside, and a recent Ph.D. graduate in Electrical and Computer Engineering from the University of California, San Diego. She is an SRC Research Scholar and recipient of the 2025 Barbara J. and Paul D. Saltman Excellent Teaching Award, as well as the 2025 Excellence in Teaching Award from UC San Diego’s Computer Science and Engineering Department. She has served as a reviewer for ACM Computing Surveys and Signal, Image and Video Processing Journal. Her research focuses on the synergy between brain-inspired Hyper dimensional Computing and Machine Learning, and innovations in Electrical and Computer Science education. Beyond the classroom, she is dedicated to mentoring students at all levels—guiding undergraduate and graduate students at UC San Diego’s System Energy Efficiency Lab and Women in Computing Center, as well as high school students at the UCSD PRISM Research Center—on research projects in Hyper dimensional Computing and Machine Learning.
Agenda
- Invited talk from Dr. Fatemeh Asgarinejad, an incoming Assistant Professor of Teaching in the Electrical and Computer Engineering Department at the University of California, Riverside.
- Q/A Session
- 9th lecture of the 2025 Invited Seminar Series (Virtual) organized by IEEE Computer Society San Diego Chapter. Previous lectures: 2023, 2024, and 2025 invited seminar series.