
A massively parallel amplitude-only Fourier neural network
Researchers invent an optical convolutional neural network accelerator for machine learning
SUMMARY
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. 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.
THE SITUATION
Global demand for machine learning hardware is dramatically outpacing current computing power supplies. State-of-the-art electronic hardware, such as graphics processing units and tensor processing unit accelerators, help mitigate this, but are intrinsically challenged by serial data processing that requires iterative data processing and encounters delays from wiring and circuit constraints. Optical alternatives to electronic hardware could 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.
THE SOLUTION
To achieve a breakthrough in this optical machine learning system, the researchers replaced 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.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Machine intelligence
- AI AI Captain! New Study Shows Humans Can’t Control Superintelligent Machineson January 14, 2021 at 1:32 am
AI is smarter than humans at specific tasks such as playing chess or solving the Schrödinger’s equation. At this rate, AI might end up as a force beyond human control.
- Artificial Intelligence Market with COVID-19 Impact in Homeland Security & Public Safety - 2020-2025on January 14, 2021 at 1:27 am
Reportlinker.com announces the release of the report "Artificial Intelligence Market with COVID-19 Impact in Homeland Security & Public Safety - 2020-2025" - Nearly every aspect of national security ...
- Ion Milling Machine Industry 2021 Market Business Growth, Demand Analysis, Emerging Trends, Key Players and Regional Forecast to 2026on January 13, 2021 at 4:12 pm
Final Report will add the analysis of the impact of COVID-19 on this industry." The global “Ion Milling Machine ...
- CallRevu uses AI & machine learning for latest dealer solution upgradeon January 13, 2021 at 11:24 am
CallRevu recently upgraded its communications intelligence (CI) solution to help dealerships monitor and improve their communications with customers.
- Premise Data Raises $85 Million to Transform Market Intelligence by Scaling its Machine Learning and Human Intelligence Platformon January 13, 2021 at 10:48 am
Premise Data today announced $85 million in Series E financing to expand its platform capabilities and global network. Led by Laurence Tosi’s WestCap Group with participation from Dave DeWalt’s ...
Go deeper with Google Headlines on:
Machine intelligence
Go deeper with Bing News on:
Machine learning hardware
- Artificial Intelligence Market with COVID-19 Impact in Homeland Security & Public Safety - 2020-2025on January 14, 2021 at 1:27 am
Reportlinker.com announces the release of the report "Artificial Intelligence Market with COVID-19 Impact in Homeland Security & Public Safety - 2020-2025" - Nearly every aspect of national security ...
- Oracle Database 21c introduces 200+ innovationson January 14, 2021 at 12:20 am
Oracle announced that Oracle Database 21c, the latest version of the world's leading converged database, is available on Oracle Cloud.
- Certification programme in Deep Learningon January 13, 2021 at 9:49 am
The Indian Institute of Science (IISc) and TalentSprint have launched a PG level Advanced Certification Programme in Deep Learning. The 10-month executive education programme will be taught by a team ...
- Intel Adds Hardware-Enabled Ransomware Detection to 11th Gen vPro Chipson January 13, 2021 at 2:11 am
Intel and Cybereason have partnered to build anti-ransomware defenses into the chipmaker's newly announced 11th generation Core vPro business-class processors. The hardware-based security enhancements ...
- Intel adds hardware-based ransomware detection to 11th gen CPUson January 11, 2021 at 6:43 pm
Intel announced today at CES 2021 that they have added hardware-based ransomware detection to their newly announced 11th generation Core vPro business-class processors.