Classification of time-domain waveforms using a speckle-based optical reservoir computer

Abstract

Reservoir computing is a recurrent machine learning framework that expands the dimensionality of a problem by mapping an input signal into a higher-dimension reservoir space that can capture and predict features of complex, non-linear temporal dynamics. Here, we report on a bulk optical demonstration of an analog reservoir computer using speckles generated by propagating a laser beam modulated with a spatial light modulator through a multimode waveguide. We demonstrate that the hardware can successfully perform a multivariate audio classification task performed using the Japanese vowel speakers public data set. We perform full wave optical calculations of this architecture implemented in a chip-scale platform using an SiO2 waveguide and demonstrate that it performs as well as a fully numerical implementation of reservoir computing. As all the optical components used in the experiment can be fabricated using a commercial photonic integrated circuit foundry, our result demonstrates a framework for building a scalable, chip-scale, reservoir computer capable of performing optical signal processing.

References in corpus (7)

• Deep Learning with Coherent Nanophotonic Circuits
• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Recent Advances in Physical Reservoir Computing: A Review
• All-optical Reservoir Computing
• Reinforcement Learning in a large scale photonic Recurrent Neural Network
• High performance photonic reservoir computer based on a coherently driven passive cavity
• Optical Reservoir Computing using multiple light scattering for chaotic systems prediction

Cited by in corpus (14)

• Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
• Scalable Optical Learning Operator
• Opportunities in Quantum Reservoir Computing and Extreme Learning Machines
• Controlling light propagation in multimode fibers for imaging, spectroscopy and beyond
• Photonic extreme learning machine by free-space optical propagation
• Photonic reservoir computer based on frequency multiplexing
• Ultra-high resolution and broadband chip-scale speckle enhanced Fourier-transform spectrometer
• A Photonic Integrated Circuit based Compressive Sensing Radio Frequency Receiver Using Waveguide Speckle
• Deep Photonic Reservoir Computer for Speech Recognition
• Short-wavelength Reverberant Wave Systems for Physical Realization of Reservoir Computing
• Optical hyperdimensional soft sensing: Speckle-based touch interface and tactile sensor
• Photonic neural field on a silicon chip: large-scale, high-speed neuro-inspired computing and sensing
• Using multidimensional speckle dynamics for high-speed, large-scale, parallel photonic computing
• A Photonic Integrated Circuit based Compressive Sensing Radio Frequency Receiver