U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Advait Madhavan (Fed)

Advait Madhavan is a UMD Assistant Research Scientist in the Alternative Computing Group in the Nanoscale Device Characterization Division of the Physical Measurement Laboratory (PML). He received a Ph.D. in Electrical and Computer Engineering from the University of California, Santa Barbara and is currently working with Mark Stiles and Jabez McClelland. His interests lie in various brain inspired approaches to computation such as temporal, analog and stochastic codes. His expertise lies in VLSI, with the objective of building chips to interface with emerging technologies in order to realize these unconventional computing paradigms.

Selected Publications

  • Madhavan, Advait, Matthew W. Daniels, and Mark D. Stiles. "Temporal state machines: Using temporal memory to stitch time-based graph computations." ACM Journal on Emerging Technologies in Computing Systems (JETC) 17.3 (2021): 1-27.
  • Race logic: A hardware acceleration for dynamic programming algorithms, Madhavan, A., Sherwood, T., & Strukov, D., ACM SIGARCH Computer Architecture News, 42(3), 517-528 (2014).
  • A 4-mm 2 180-nm-CMOS 15-Giga-cell-updates-per-second DNA sequence alignment engine based on asynchronous race conditions, Madhavan, A., Sherwood, T., & Strukov, D., In Custom Integrated Circuits Conference (CICC), 2017 IEEE (pp. 1-4). IEEE (2017, April).

Publications

Layer ensemble averaging for fault tolerance in memristive neural networks

Author(s)
Osama Yousuf, Brian Hoskins, Karthick Ramu, Mitchell Fream, William Borders, Advait Madhavan, Matthew Daniels, Andrew Dienstfrey, Jabez McClelland, Martin Lueker-Boden, Gina Adam
Advancements in continual learning with artificial neural networks have been fueled in large part by scaling network dimensionalities. As this scaling continues

Measurement-driven Langevin modeling of superparamagnetic tunnel junctions

Author(s)
Liam Pocher, Temitayo Adeyeye, Sidra Gibeault, Philippe Talatchian, Ursula Ebels, Daniel Lathrop, Jabez J. McClelland, Mark Stiles, Advait Madhavan, Matthew Daniels
Superparamagnetic tunnel junctions are important devices for a range of emerging technologies, but most existing compact models capture only their mean
View more Publications

Patents (2018-Present)

Quasi-Systolic Processor and Quasi-Systolic Array

NIST Inventors
Matthew Daniels , Mark D. Stiles and Advait Madhavan
A quasi-systolic array includes: a primary quasi-systolic processor; an edge row bank and edge column bank of edge quasi-systolic processors; and an interior bank of interior quasi-systolic processors. The primary quasi-systolic processor, edge quasi-systolic processor, and interior quasi-systolic

Timing-Based Computer Architecture Systems And Methods

NIST Inventors
Advait Madhavan , Mark D. Stiles and Matthew Daniels
Tropical algebra is an emerging field of mathematics concerned with graph theory, control theory, and certain optimization problems, especially in discrete event systems. We developed a novel computer circuit called a tropical state machine that uses signal timing and the physics of nanodevices to
View All Patents
Created August 15, 2019, Updated December 9, 2022