MIT Technology Review
Making AI algorithms crazy fast using chips powered by light
Optical chips have been tried before—but the rise of deep learning may offer an opportunity to succeed where others have failed.
By Will Knight
Inside a small laboratory in Boston’s seaport district, buried within a jumble of lasers, lenses, mirrors, and a tangle of wiring, is a tiny chip that might be about to have a big impact on the world of artificial intelligence.
The lab belongs to Lightelligence, a startup that’s developing a radically new kind of AI accelerator chip. Instead of using electrons to carry out the core mathematical computations needed for machine learning, the company’s prototype device uses light.
Lightelligence announces the hiring of Maurice (Mo) Steinman as VP of Engineering. Mo, who departed as Sr. Fellow at AMD, will lead Lightelligence’s engineering efforts. With his deep industry experience at leading semiconductor companies, Mo brings the technical management experience required to continue to scale Lightelligence’s engineering teams which consist of photonics, electronics, and algorithms.
Mo has enjoyed a career in the tech industry lasting more than three decades, working for such companies as Digital, Compaq, HP, Intel and most recently AMD, where he held the title of Sr. Fellow. A veteran of many successful tapeouts and product introductions, Mo has expertise in System on Chip (SoC) architecture, SoC interconnect, memory subsystems, and power management. Mo graduated from Rensselaer Polytechnic Institute (RPI) with a BS in Computer & Systems Engineering and holds over 40 computer architecture patents.
Artificial neural networks, computer algorithms that take inspiration from the human brain, have demonstrated fancy feats such as detecting lies, recognizing faces, and predicting heart attacks. But most computers can’t run them efficiently. Now, a team of engineers has designed a computer chip that uses beams of light to mimic neurons. Such “optical neural networks” could make any application of so-called deep learning—from virtual assistants to language translators—many times faster and more efficient...
“Deep learning” computer systems, based on artificial neural networks that mimic the way the brain learns from an accumulation of examples, have become a hot topic in computer science. In addition to enabling technologies such as face- and voice-recognition software, these systems could scour vast amounts of medical data to find patterns that could be useful diagnostically, or scan chemical formulas for possible new pharmaceuticals...