Fourier-based convolutional neural network accelerator (Conference Presentation)

Volker J. Sorger

doi:10.1117/12.2633918

3 October 2022 Fourier-based convolutional neural network accelerator (Conference Presentation)

Volker J. Sorger

Proceedings Volume PC12225, Optics and Photonics for Information Processing XVI; PC1222505 (2022) https://doi.org/10.1117/12.2633918
Event: SPIE Optical Engineering + Applications, 2022, San Diego, California, United States

Abstract

Decision-making by artificial neural networks with minimal latency is paramount for numerous applications such as navigation, tracking, and real-time machine action systems. This requires the machine learning hardware to handle multidimensional data with a high throughput. Processing convolution operations being the major computational tool for data classification tasks, unfortunately, follows a challenging run-time complexity scaling law. However, implementing the convolution theorem homomorphically in a Fourier-optic display-light-processor enables a non-iterative O(1) runtime complexity for data inputs beyond 1,000 × 1,000 large matrices. Following this approach, here we demonstrate data streaming multi-kernel image batch-processing with a Fourier Convolutional Neural Network (FCNN) accelerator. We show image batch processing of large-scale matrices as passive 2-million dot-product multiplications performed by digital light-processing modules in the Fourier domain. In addition, we parallelize this optical FCNN system further by utilizing multiple spatio-parallel diffraction orders, thus achieving a 98-times throughput improvement over state-of-art FCNN accelerators. The comprehensive discussion of the practical challenges related to working on the edge of the system’s capabilities highlights issues of crosstalk in Fourier domain and resolution scaling laws. Accelerating convolutions by utilizing the massive parallelism in display technology brings forth a non-van Neuman-based machine learning acceleration.

Conference Presentation

Citation Download Citation

Volker J. Sorger "Fourier-based convolutional neural network accelerator (Conference Presentation)", Proc. SPIE PC12225, Optics and Photonics for Information Processing XVI, PC1222505 (3 October 2022); https://doi.org/10.1117/12.2633918

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