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
- Self-checkout machines face ban in California with new bill aimed at curbing theft
A new California bill has the potential to ban self-checkout options in grocery stores in an attempt to curb retail theft. Senate Bill 1446, introduced by Democratic state Sen. Lola Smallwood-Cuevas, ...
- Human Expertise Meets Machine Intelligence: The Winning Formula for Modern Financial Planning
Learn how AI is augmenting, not replacing, human advisors. Discover how this collaboration is creating a more robust and personalized financial planning experience.
- Circles of intelligence: How AI is redefining human creativity
Rather than relegating human intelligence, the growth of AI will leave aside higher-order social, economic, and business problems for our finest minds to tackle. This is the message business leaders ...
- Machine learning engineer salary: How much do AI techs make?
Machine learning engineers tend to be among the highest-paid employees in tech. Here’s how much they make and which companies pay the most.
- Geospatial intelligence gets smart
How the National Geospatial Intelligence Agency is leveraging AI for battlefield awareness and geopolitical insights.
Go deeper with Google Headlines on:
Machine intelligence
[google_news title=”” keyword=”machine intelligence” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Machine learning hardware
- SpiNNcloud Systems Unveils Innovative Neuromorphic Supercomputer SpiNNaker2
Discover SpiNNaker2, a revolutionary brain-inspired AI supercomputer by SpiNNcloud Systems, offering unmatched performance and efficiency.
- Apple Enters AI Race with Powerful Processor
Key to the M4’s high performance is an IP block in the chip dedicated to the acceleration of AI workloads. Apple said the engine can process up to 38 trillion operations per second, that is reportedly ...
- Machine learning aids in discovery of sperm whale ‘alphabet’
Researchers at MIT CSAIL and Project CETI believe that they have unlocked a kind of sperm whale alphabet with the aid of machine learning technologies.
- DigiKey Sponsors EW Project Challenge 2024 by ElectronicWings
DigiKey also supports engineers, designers, builders and procurement professionals with a wealth of digital solutions, frictionless interactions and tools to make their jobs more efficient.
- New Grid-EYE – 90° from Panasonic increases field of vision for Machine Learning based IR sensing
Panasonic Industry has launched a new member of its popular Grid-EYE sensor family featuring a 90° lens delivering a wider field of view (FoV) and reducing the number of sensors required to cover a ...
Go deeper with Google Headlines on:
Machine learning hardware
[google_news title=”” keyword=”machine learning hardware” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]