Accelerating AI and Machine Learning Using Light
Congratulations to Nathan Youngblood and his colleagues, who recently received a $1.2 million 4-year grant from the NSF to develop a new type of computer chip that uses laser light for AI and machine learning computation.
AI and machine learning’s rapid growth in sophistication and large-scale implementation has caused the demand for computing power to increase at a rate where conventional computing paradigms and hardware platforms are struggling to keep up.
The chip, called a “hybrid co-processing unit” or HCU, aims to address this challenge by combining traditional electronics with photonics and using light generated by lasers instead of electricity for data processing. This will greatly accelerate the computing speed and efficiency of AI and machine learning applications, while at the same time reducing energy consumption.
The team will be fabricating thousands of photonic elements and millions of transistors together in a cost-effective and scalable manner as well as building computer models to simulate every aspect of the device. By 2025, they expect to have a working, physical prototype and be poised to manufacture the device in larger quantities and at a scale capable of moving into the marketplace.
Read some of their recent work here!