How to utilize physics to enhance artificial intelligence

Bahram Jalali; Achuta Kadambi; Vwani Roychowdhuri

doi:10.1117/12.2578837

5 March 2021 How to utilize physics to enhance artificial intelligence

Bahram Jalali, Achuta Kadambi, Vwani Roychowdhuri

Proceedings Volume 11680, Physics and Simulation of Optoelectronic Devices XXIX; 116800F (2021) https://doi.org/10.1117/12.2578837
Event: SPIE OPTO, 2021, Online Only

Abstract

Deep neural networks exploit millions or more free parameters that are tuned to a requisite large and curated dataset. The black-box nature of these models masks interpretability and the ability to diagnose failures. Although astonishing performance gains are being achieved, these come at the expense of exponential rise in computation and memory utilization. This talk will review how the emerging convergence of physics and neural networks will confront these challenges, extend the rise of artificial intelligence, and create opportunities for scientific discoveries.

Conference Presentation

Citation Download Citation

Bahram Jalali, Achuta Kadambi, and Vwani Roychowdhuri "How to utilize physics to enhance artificial intelligence", Proc. SPIE 11680, Physics and Simulation of Optoelectronic Devices XXIX, 116800F (5 March 2021); https://doi.org/10.1117/12.2578837

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
PRESENTATION

WATCH
PRESENTATION SAVE TO MY LIBRARY

GET CITATION

KEYWORDS

Artificial intelligence

Physics

Neural networks

Optical design

Differential equations

Diffraction

Diffusion

Show All Keywords

RELATED CONTENT

Terahertz optical logic calculation based on diffraction neural network
Proceedings of SPIE (July 22 2022)

A neural network to explore the Fresnel diffraction of a...
Proceedings of SPIE (June 30 2022)

Fast fault localization based on deep learning in optical networks
Proceedings of SPIE (April 04 2023)

Optical design using physics-inspired neural networks
Proceedings of SPIE (January 01 1900)

Investigations of self reproduction of field diffracted by two dimensional...
Proceedings of SPIE (November 30 2015)

Deep learning based failure prediction with data augmentation in optical...
Proceedings of SPIE (February 14 2019)

Generalized design of diffractive optical elements using neural networks
Proceedings of SPIE (November 16 2004)

Subscribe to Digital Library

Receive Erratum Email Alert

Show All Keywords

Keywords/Phrases

Search In:

Publication Years