Optical neural network via loose neuron array and functional learning
Open Access
- 3 May 2023
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-12
Abstract
This research proposes a deep-learning paradigm, termed functional learning (FL), to physically train a loose neuron array, a group of non-handcrafted, non-differentiable, and loosely connected physical neurons whose connections and gradients are beyond explicit expression. The paradigm targets training non-differentiable hardware, and therefore solves many interdisciplinary challenges at once: the precise modeling and control of high-dimensional systems, the on-site calibration of multimodal hardware imperfectness, and the end-to-end training of non-differentiable and modeless physical neurons through implicit gradient propagation. It offers a methodology to build hardware without handcrafted design, strict fabrication, and precise assembling, thus forging paths for hardware design, chip manufacturing, physical neuron training, and system control. In addition, the functional learning paradigm is numerically and physically verified with an original light field neural network (LFNN). It realizes a programmable incoherent optical neural network, a well-known challenge that delivers light-speed, high-bandwidth, and power-efficient neural network inference via processing parallel visible light signals in the free space. As a promising supplement to existing power- and bandwidth-constrained digital neural networks, light field neural network has various potential applications: brain-inspired optical computation, high-bandwidth power-efficient neural network inference, and light-speed programmable lens/displays/detectors that operate in visible light.Keywords
This publication has 23 references indexed in Scilit:
- Deep learningNature, 2015
- Tensor displaysACM Transactions on Graphics, 2012
- High speed and slow motion: the technology of modern high speed camerasPhysics Education, 2011
- Monolayer graphene as a saturable absorber in a mode-locked laserNano Research, 2010
- Sub-femtojoule all-optical switching using a photonic-crystal nanocavityNature Photonics, 2010
- Optimal bistable switching in nonlinear photonic crystalsPhysical Review E, 2002
- Optical bistability in finite-size nonlinear bidimensional photonic crystals doped by a microcavityPhysical Review B, 2000
- Nonlinear mirror based on two-photon absorptionJournal of the Optical Society of America B, 1997
- Experimental observations of bistability and instability in a two-dimensional nonlinear optical superlatticePhysical Review Letters, 1993
- Pulse transmission through a saturable absorberBritish Journal of Applied Physics, 1967