Transcript
According to a recent report from McKinsey, spending on machine learning applications recently skyrocketed to $165B annually. But, before a machine can perform intelligent tasks such as recognizing the details of an image, it must be trained. Training of modern-day artificial intelligence systems like Tesla’s autopilot costs several million dollars in electric power consumption and requires supercomputer-like infrastructure. This surging AI "appetite" leaves an ever-widening gap between computer hardware and demand for AI.
Photonic integrated circuits, often called optical chips, have emerged as a possible solution to deliver higher computing performance, as measured by the number of operations performed per second per watt used. However, though they’ve demonstrated improved core operations in applications like data classification, photonic chips have yet to improve the actual front-end learning and machine training process.
Machine learning is a two-step procedure. First, data is used to train the system and then other data is used to test the performance of the AI system. In new research published in the journal Optica, a team of researchers set out to do just that. After one training step, the team observed an error and reconfigured the hardware for a second training cycle followed by additional training cycles until the system was able to correctly label objects appearing in a movie.
Previously, photonic chips have only demonstrated an ability to classify and infer information from data. But now, researchers have made it possible to speed up the training step itself. This added AI capability is part of a larger effort around photonic tensor cores and other electronic-photonic application-specific integrated circuits that leverage photonic chip manufacturing for machine learning and AI applications.
This novel hardware will speed up the training of machine learning systems and harness the best of what both photonics and electronic chips have to offer. This represents a major leap forward for AI hardware acceleration.
|
