Free-space optical neural network based on thermal atomic nonlinearity

Abstract

As artificial neural networks (ANNs) continue to make strides in wide-ranging and diverse fields of technology, the search for more efficient hardware implementations beyond conventional electronics is gaining traction. In particular, optical implementations potentially offer extraordinary gains in terms of speed and reduced energy consumption due to intrinsic parallelism of free-space optics. At the same time, a physical nonlinearity, a crucial ingredient of an ANN, is not easy to realize in free-space optics, which restricts the potential of this platform. This problem is further exacerbated by the need to perform the nonlinear activation also in parallel for each data point to preserve the benefit of linear free-space optics. Here, we present a free-space optical ANN with diffraction-based linear weight summation and nonlinear activation enabled by the saturable absorption of thermal atoms. We demonstrate, via both simulation and experiment, image classification of handwritten digits using only a single layer and observed 6-percent improvement in classification accuracy due to the optical nonlinearity compared to a linear model. Our platform preserves the massive parallelism of free-space optics even with physical nonlinearity, and thus opens the way for novel designs and wider deployment of optical ANNs.

References in corpus (9)

• Deep Learning with Coherent Nanophotonic Circuits
• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• All Optical Neural Network with Nonlinear Activation Functions
• Digital Electronics and Analog Photonics for Convolutional Neural Networks (DEAP-CNNs)
• Varifocal zoom imaging with large area focal length adjustable metalenses
• Wavefront shaping in complex media at 350 KHz with a 1D-to-2D transform
• Polaritonic neuromorphic computing outperforms linear classifiers
• An Optical Frontend for a Convolutional Neural Network
• Image amplification in a self-imaging degenerate optical cavity

Cited by in corpus (13)

• Image sensing with multilayer, nonlinear optical neural networks
• Photonics for Neuromorphic Computing: Fundamentals, Devices, and Opportunities
• Nonlinear optical encoding enabled by recurrent linear scattering
• Hot atomic vapors for nonlinear and quantum optics
• Knowledge Distillation Circumvents Nonlinearity for Optical Convolutional Neural Networks
• Transferable polychromatic optical encoder for neural networks
• Realistic quantum photonic neural networks
• Optical convolutional neural network with atomic nonlinearity
• Free-Space Optical Spiking Neural Network
• Engineering nonlinear activation functions for all-optical neural networks via quantum interference
• Sub-quadratic scalable approximate linear converter using multi-plane light conversion with low-entropy mode mixers
• Forming complex neurons by four-wave mixing in a Bose-Einstein condensate
• High speed and reconfigurable optronic neural network with digital nonlinear activation