Circuits that train themselves: decentralized, physics-driven learning

Sam Dillavou; Benjamin Beyer; Menachem Stern; Marc Z. Miskin; Andrea J. Liu; Douglas J. Durian

doi:10.1117/12.2648618

15 March 2023 Circuits that train themselves: decentralized, physics-driven learning

Sam Dillavou, Benjamin Beyer, Menachem Stern, Marc Z. Miskin, Andrea J. Liu, Douglas J. Durian

Proceedings Volume 12438, AI and Optical Data Sciences IV; 124380G (2023) https://doi.org/10.1117/12.2648618
Event: SPIE OPTO, 2023, San Francisco, California, United States

Abstract

In typical artificial neural networks, neurons adjust according to global calculations of a central processor, but in the brain neurons and synapses self-adjust based on local information. A man-made self-adjusting (distributed) system capable of performing machine-learning problems would have substantial scaling advantages over typical computational neural networks, in power consumption, speed, and robustness to damage. Furthermore, such a system would allow us to study physical learning without the added complexity of biology. Here we unveil the second-generation design of such a system – a transistor-based self-adjusting analog network that trains itself to perform a wide variety of tasks. Here we demonstrate basic features of the system, including the ability to monitor all internal states. This platform is already faster than a simulation of itself, and is thus an exciting platform for the investigation of physical learning.

Conference Presentation

Citation Download Citation

Sam Dillavou, Benjamin Beyer, Menachem Stern, Marc Z. Miskin, Andrea J. Liu, and Douglas J. Durian "Circuits that train themselves: decentralized, physics-driven learning", Proc. SPIE 12438, AI and Optical Data Sciences IV, 124380G (15 March 2023); https://doi.org/10.1117/12.2648618

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available