Photonic extreme learning machine by free-space optical propagation

Abstract

Photonic brain-inspired platforms are emerging as novel analog computing devices, enabling fast and energy-efficient operations for machine learning. These artificial neural networks generally require tailored optical elements, such as integrated photonic circuits, engineered diffractive layers, nanophotonic materials, or time-delay schemes, which are challenging to train or stabilize. Here we present a neuromorphic photonic scheme - photonic extreme learning machines - that can be implemented simply by using an optical encoder and coherent wave propagation in free space. We realize the concept through spatial light modulation of a laser beam, with the far field that acts as feature mapping space. We experimentally demonstrated learning from data on various classification and regression tasks, achieving accuracies comparable to digital extreme learning machines. Our findings point out an optical machine learning device that is easy-to-train, energetically efficient, scalable and fabrication-constraint free. The scheme can be generalized to a plethora of photonic systems, opening the route to real-time neuromorphic processing of optical data.

arXiv comment12 pages, 4 figures

References in corpus (24)

• Deep Learning with Coherent Nanophotonic Circuits
• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Parallel convolution processing using an integrated photonic tensor core
• 11 TeraFLOPs per second photonic convolutional accelerator for deep learning optical neural networks
• Neuromorphic Silicon Photonic Networks
• Training of photonic neural networks through in situ backpropagation
• All Optical Neural Network with Nonlinear Activation Functions
• Reinforcement Learning in a large scale photonic Recurrent Neural Network
• Large-Scale Optical Neural Networks based on Photoelectric Multiplication
• Wave Physics as an Analog Recurrent Neural Network
• Programmable Phase-change Metasurfaces on Waveguides for Multimode Photonic Convolutional Neural Network
• Large-scale photonic Ising machine by spatial light modulation
• Design of Task-Specific Optical Systems Using Broadband Diffractive Neural Networks
• High performance photonic reservoir computer based on a coherently driven passive cavity
• Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
• Theory of neuromorphic computing by waves: machine learning by rogue waves, dispersive shocks, and solitons
• Human action recognition with a large-scale brain-inspired photonic computer
• Wavefront shaping in complex media at 350 KHz with a 1D-to-2D transform
• Nanophotonic spin-glass for realization of a coherent Ising machine
• Fully reconfigurable coherent optical vector-matrix multiplication
• Scalable spin-glass optical simulator
• Classification of time-domain waveforms using a speckle-based optical reservoir computer
• Fast Generation and Detection of Spatial Modes of Light using an Acousto-Optic Modulator
• Machine learning with observers predicts complex spatiotemporal behavior

Cited by in corpus (15)

• Photonic neural networks based on integrated silicon microresonators
• Optical Generative Models
• Photonic Extreme Learning Machine based on frequency multiplexing
• An array of microresonators as a Photonic Extreme Learning Machine
• Wave-based extreme deep learning based on non-linear time-Floquet entanglement
• Noisy Quantum Kernel Machines
• Tackling Sampling Noise in Physical Systems for Machine Learning Applications: Fundamental Limits and Eigentasks
• Efficient estimation of trainability for variational quantum circuits
• Photonic kernel machine learning for ultrafast spectral analysis
• Optical neuromorphic computing via temporal up-sampling and trainable encoding on a telecom device platform
• Integrated Random Projection and Dimensionality Reduction by Propagating Light in Photonic Lattices
• Free-Space Optical Spiking Neural Network
• Machine learning via relativity-inspired quantum dynamics
• Shannon Entropy Helps Optimize the Performance of a Frequency-Multiplexed Extreme Learning Machine
• All-fiber microendoscopic polarization sensing at single-photon level aided by deep-learning