That means it’s great for adding things up — but terrible for the nonlinear twists AI needs. While many teams developed light-power chips capable of handling linear mathematics, none managed ...

Penn Engineers have developed the first programmable chip that can train nonlinear neural networks using light—a breakthrough that could dramatically speed up AI training, reduce energy use and ...

Penn Engineers have developed the first programmable chip that can train nonlinear neural networks using light — a breakthrough that could dramatically speed up AI training, reduce energy use and even ...

Imagine supercomputers that think with light instead of electricity. That s the breakthrough two European research teams have ...

By enabling deep learning to run at the speed of light, this chip could allow edge devices to perform real-time data analysis ...

The Emeryville, California-based startup is developing a networking chip that utilizes optical technology to transmit data between AI chips as a form of light ... have an ace up its sleeve ...

Apple may adopt generative AI for chip design, leveraging tools from EDA firms like Synopsys and Cadence to boost speed and ...

Specifically, both use light to perform matrix multiplication, a fundamental operation in most AI processing as well ... combines a photonic and electronic chip to speed up computation for ...

SAN FRANCISCO, March 31 (Reuters) - Lightmatter, a startup valued at $4.4 billion, on Monday released two pieces of technology aimed at speeding up the connections between artificial intelligence ...

SAN FRANCISCO (Reuters) - Lightmatter, a startup valued at $4.4 billion, on Monday released two pieces of technology aimed at speeding up ... chips to power chatbots, image generators and other AI ...