Researchers report building photonic computing chips that use light pulses to train spiking neural networks on robotic-control-style benchmark tasks, aiming to shift more of the learning workload from ...

Google has taken a big leap forward with the speed of its machine learning systems by creating its own custom chip that it’s been using for over a year. The company was rumored to have been designing ...

In recent decades, computer scientists have been developing increasingly advanced machine learning techniques that can learn to predict specific patterns or effectively complete tasks by analyzing ...

Phone makers soon may get the chance to add machine learning chips into devices. ARM announced it will start offering machine learning and dedicated object detection processors. Read the whole story ...

At 180 teraflops, Google's Cloud TPU packs more punch, at least by that one measure, than the Volta-powered Tesla V100 at 120 teraflops (trillion floating point operations per second). However, until ...

SiMa.ai, the San Jose-based developer of machine learning system-on-chip platforms, will be working with the Taipei-based Lanner Electronics Inc., and AWL, the Hokkaido, Japan-based AI video analysis ...

With extreme design complexity pressure and a shrinking workforce of skilled engineers, chip designers are looking for ways to tighten schedules while maintaining quality. Machine learning methods may ...