MENU

Optical neural network accelerator for machine learning

Optical neural network accelerator for machine learning

Technology News |
By Jean-Pierre Joosting



Researchers at the George Washington University, together with researchers at the University of California, Los Angeles, and the deep-tech venture startup Optelligence LLC, have developed an optical convolutional neural network accelerator capable of processing large amounts of information, on the order of petabytes, per second.

Machine learning hardware requires a huge amount of computing power supplies. Graphics and tensor processing accelerators help address this, but are intrinsically challenged by serial data processing that requires iterative data processing and encounters delays from wiring and circuit constraints. Optical alternatives could also help speed up machine learning processes by simplifying the way information is processed in a non-iterative way. However, photonic-based machine learning is typically limited by the number of components that can be placed on photonic integrated circuits, limiting the interconnectivity, while free-space spatial-light-modulators are restricted to slow programming speeds.

Researchers achieved a breakthrough in optical machine learning by replacing spatial light modulators with digital mirror-based technology, thus developing a system over 100 times faster. The non-iterative timing of this processor, in combination with rapid programmability and massive parallelization, enables this optical machine learning system to outperform even the top-of-the-line graphics processing units by over one order of magnitude, with room for further optimization beyond the initial prototype.

Unlike the current paradigm in electronic machine learning hardware that processes information sequentially, this processor uses the Fourier optics, a concept of frequency filtering which allows for performing the required convolutions of the neural network as much simpler element-wise multiplications using the digital mirror technology.


According to Volker Sorger, associate professor of electrical and computer engineering at the George Washington University, ”This massively parallel amplitude-only Fourier optical processor is heralding a new era for information processing and machine learning. We show that training this neural network can account for the lack of phase information”

Puneet Gupta, professor and vice chair of computer engineering at UCLA commented, ”Optics allows for processing large-scale matrices in a single time-step, which allows for new scaling vectors of performing convolutions optically.”

This innovation, which harnesses the massive parallelism of light, heralds a new era of optical signal processing for machine learning with numerous applications, including in self-driving cars, 5G networks, data-centers, biomedical diagnostics, data-security and more.

Hamed Dalir, Co-founder, Optelligence LLC says, ”This prototype demonstration shows a commercial path for optical accelerators ready for a number of applications like network-edge processing, data-centers and high-performance compute systems.”

The paper, “Massively Parallel Amplitude-Only Fourier Neural Network” was published in the journal OPTICA.

https://dx.doi.org/10.1364/OPTICA.408659

 

Further reading

CEA-Leti to build quantum-photonics platform
Enea machine learning delivers 15% RAN capacity increase
EU project boasts 100x energy efficiency in edge computing
Anritsu gets patent for automated anomaly detection algorithm
Mobile network automation startup secures $32M Series B financing

If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News

Share:

Linked Articles
10s