Prizes 2023

15 December, 2023

2023 Misha Mahowald Prizes

The juries have awarded a lifetime contribution award to Carver Mead and have awarded the Misha Mahowald prize to a team from Sandia National Labs.

Watch the Prize Introductions and Award presentations at NICE 2024 (T Delbruck)

7 December, 2023

Misha Mahowald Recognition of Lifetime Contribution to Neuromorphic Engineering

This special award is conferred on Prof. Carver Mead, Gordon and Betty Moore Professor Emeritus of Engineering and Applied Science at the California Institute of Technology.

Jury citation: "Carver Mead established the field of Neuromorphic Electronic Engineering. His creativity and vision has inspired a generation of scientists, technologists, and entrepreneurs  to emulate brain-like information processing in electronic systems."

Extended citation: Mead evolved a deep and intuitive understanding of the physics of transistors, and laid the foundations for systematically organizing them into large scale digital computing systems embedded in silicon chips. He extended his insights to questions of biological computation: firstly by understanding the biophysics of voltage-sensitive nerve channels, and then by identifying more general  analogies between the physics of transistors and that of neurons.  His goal was to understand the natural computation processes of brains and to apply this knowledge practically in the development of more efficient means of electronic computing.  Working with Misha Mahowald, he developed the first large-scale integrated silicon retina chips that use the organizational and functional principles of biological neural information processing. In so doing, Carver established the fundamental concepts and practices of a novel approach to brain-like computation, now known as Neuromorphic Electronic Engineering.   During the decade spanning roughly 1985-1995, he and his students at Caltech’s Physics of Computation Lab pioneered the first integrated silicon retinas, silicon cochleas, silicon neurons and synapses, non-volatile floating gate synaptic memories, central pattern generators, and the first systems that communicated information between chips via asynchronous action potential-like address-event spikes. His 1989 book “Analog VLSI and Neural Systems“ and his CNS182 course taught these concepts and methods to a new generation of researchers. He co-founded companies to bring these and other research concepts to mass production. The generation of students he inspired now lead neuromorphic research and education in academia, government, and industry throughout the world. 

Watch Carver Mead's acceptance speech

28 November, 2023

Misha Mahowald Prize

The jury awarded the 2023 Prize to a team from the Sandia National Laboratories for the project "Neuromorphic Advantage for Discrete-Time Markov Chain Random Walks"

Jury citation: "The Sandia team demonstrated that neuromorphic hardware can efficiently implement Monte Carlo methods for solving differential equations.  Monte Carlo methods are used for solving a wide range of problems including those in heat transfer, medical imaging and finance."

The work is best summarized in their paper “Neuromorphic scaling advantage for energy-efficient random walk computations”, Nature Electronics 5.2 (2022)

The team members at the  Neural Exploration & Research Laboratory in the  Center for Computing Research are James Bradley Aimone, Brian C. Franke, Richard B. Lehoucq, Michael C. Krygier, Aaron J. Hill, Ojas Parekh, Leah E. Reeder, William Severa, and J. Darby Smith. The PI of this project is Brad Aimone.

From top left: Darby Smith, Leah Reeder, Rich Lehoucq, Brian Franke, Ojas Parekh. 2nd row: William Severa, Brad Aimone, Michael Krygier, Aaron Hill

Random walk example applications demonstrating (a) heat diffusion across a torus and (b) modeled spread of an invasive species from a single origination point. Adapted from award submission.

Their project includes work from three projects funded through Sandia National Laboratories’ Laboratory Directed Research and Development Program and has also been supported, in part, by the Department of Energy’s Advanced Simulation and Computing Program. Additionally, this effort leverages neuromorphic hardware procured through the Department of Energy’s Advanced Simulation and Computing program.

Neuromorphic Markov random walk implementations (TrueNorth and Loihi) are slower than CPU or GPU but burn much less energy per update. Adapted from Smith et al. 2022.

25 November, 2023

Mahowald Early Career Award

The MECA jury was unable to select a suitable winner for the Award in 2023.