Make your plans to attend
Vaccination required
>
Conference 11999 > Paper 11999-30
Paper 11999-30

FemtoComputing: machine learning using femtosecond pulses and nonlinear optics

Abstract

We report a new concept in hardware acceleration of AI that exploits femtosecond pulses for both data acquisition and computing. Data is first modulated onto the spectrum of a supercontinuum laser. Nonlinear optical propagation then projects the data into an intermediate space in which data classification accuracy is enhanced. This nonlinear optical kernel operation improves the linear classification results similar to a traditional numerical kernel (such as the radial-basis-function) but with orders of magnitude lower latency. The performance is data-dependent due to the limited degrees of freedom in the optical part of the system.

Presenter

UCLA Samueli School of Engineering (United States)
Presenter/Author
UCLA Samueli School of Engineering (United States)
Author
Tingyi Zhou
UCLA Samueli School of Engineering (United States)
Author
Fabien Scalzo
Univ. of California, Los Angeles (United States)