Light-powered silicon chip technology funded $11 million to enable next-generation AI

Share this on social media:

MIT spin-off Lightmatter has received $11 million in series A funding to accelerate the development of an ultra-efficient silicon chip that processes using light, rather than electricity, to enable a faster and more efficient form of artificial intelligence (AI) that promises orders of magnitude performance improvements over what is currently feasible using existing technologies.

AI powers products ranging from online advertising to intelligent personal assistants, using models that first have to be ‘trained’ with large datasets — a process that requires a lot of time and energy with existing computer processors. As AI algorithms continue to develop however, current technologies will struggle to keep up with the increasing demand for computing power. Faster and more energy efficient computers are therefore needed to power the next generation of AI, which is what Lightmatter intends to accomplish with its new chip technology.

‘For decades, electronic computers have been at the foundation of the computational progress that has ultimately enabled the AI revolution, but AI algorithms have a voracious appetite for computational power,’ said Dr Nicholas Harris, CEO of Lightmatter. ‘AI is really in its infancy, and to move forward, new enabling technologies are required. At Lightmatter, we are augmenting electronic computers with photonics to power a fundamentally new kind of computer that is efficient enough to propel the next generation of AI.’

The $11 million funding round was co-led by Matrix Partners and Spark Capital, with Matrix’s Stan Reiss and Spark’s Santo Politi also having joined Lightmatter’s board of directors.

‘It is rare to see true innovation in the chip industry today, but Lightmatter has done it. The importance of this groundbreaking technology cannot be overstated,’ commented Reiss. ‘The Lightmatter team has applied a major scientific discovery to dramatically increase the power of AI and its reach into our lives.’

‘We’re already feeling the impact and benefits of artificial intelligence in our daily lives and yet we are still clearly in the early days of what is possible,’ said Politi. ‘For true advances in AI to occur, massive leaps forward in computational power will be required. I’m delighted to invest in the team at Lightmatter whose breakthrough will usher us into this future.’

Last year Lightmatter took home the Robert P. Goldberg $100,000 grand prize at the MIT $100K Entrepreneurship Competition's Launch Finale after prevailing over seven teams of finalists.

Related news

28 July 2021

PsiQuantum has developed technology in which single photons are manipulated using photonic circuits which are patterned onto a silicon chip using standard semiconductor manufacturing processes

18 June 2021

The paper demonstrates the technical feasibility of integrating CMOS switching functionality with single-mode optical interfaces within the same package

Schematic of three different nano flashlights for the generation of (left to right) focused, wide-spanning, and collimated light beams. Credit: Robin Singh

13 May 2021

The device was created using using existing fabrication technologies familiar to the microelectronics industry