Parallel Implementation Of Nonlinear Functions Using An Optical Processor (UCLA)
Researchers at UCLA have published a technical paper titled “Massively parallel and universal approximation of nonlinear functions using diffractive processors,” showcasing a novel approach to implementing nonlinear functions optically. By utilizing optimized diffractive processors with passive phase-only surfaces, large-scale nonlinear computation can be achieved using linear optics. This framework allows for the parallel computation of one million distinct nonlinear functions at wavelength-scale spatial density, demonstrating the potential for diffractive optical processors to serve as a scalable platform for universal nonlinear function approximation. The research also successfully approximated 35 unique nonlinear functions experimentally, showcasing the capabilities of this optical computing system.