All-optical nonlinear activation function based on stimulated Brillouin scattering

Abstract

Photonic neural networks have demonstrated their potential over the past decades, but have not yet reached the full extent of their capabilities. One reason for this lies in an essential component - the nonlinear activation function, which ensures that the neural network can perform the required arbitrary nonlinear transformation. The desired all-optical nonlinear activation function is difficult to realize, and as a result, most of the reported photonic neural networks rely on opto-electronic activation functions. Usually, the sacrifices made are the unique advantages of photonics, such as resource-efficient coherent and frequency-multiplexed information encoding. In addition, opto-electronic activation functions normally limit the photonic neural network depth by adding insertion losses. Here, we experimentally demonstrate an in-fiber photonic nonlinear activation function based on stimulated Brillouin scattering. Our design is coherent and frequency selective, making it suitable for multi-frequency neural networks. The optoacoustic activation function can be tuned continuously and all-optically between a variety of activation functions such as LeakyReLU, Sigmoid, and Quadratic. In addition, our design amplifies the input signal with gain as high as $20\mathrm{dB}$, compensating for insertion losses on the fly, and thus paving the way for deep optical neural networks.

References in corpus (30)

• Deep Learning with Coherent Nanophotonic Circuits
• Parallel convolution processing using an integrated photonic tensor core
• Photonics for artificial intelligence and neuromorphic computing
• Integrated Waveguide Brillouin Laser
• Sub-Hz Linewidth Photonic-Integrated Brillouin Laser
• Non-Reciprocal Brillouin Scattering Induced Transparency
• Interaction between light and highly confined hypersound in a silicon photonic nanowire
• Reprogrammable Electro-Optic Nonlinear Activation Functions for Optical Neural Networks
• Learning Activation Functions to Improve Deep Neural Networks
• Collapse of Deep and Narrow Neural Nets
• Large Brillouin Amplification in Silicon
• Dying ReLU and Initialization: Theory and Numerical Examples
• A silicon Brillouin laser
• Observation of Spontaneous Brillouin Cooling
• Delocalized Photonic Deep Learning on the Internet's Edge
• Single chip photonic deep neural network with accelerated training
• Deep Learning with Coherent VCSEL Neural Networks
• Control of coherent information via on chip photonic-phononic emitter-receivers
• A chip-integrated coherent photonic-phononic memory
• Observation of stimulated Brillouin scattering in silicon nitride integrated waveguides
• Visible light photonic integrated Brillouin laser
• Surface acoustic wave photonic devices in silicon on insulator
• Arbitrary linear transformations for photons in the frequency synthetic dimension
• Observation of Brillouin optomechanical strong coupling with an 11 GHz mechanical mode
• A Hamiltonian treatment of stimulated Brillouin scattering in nanoscale integrated waveguides
• Non-Gaussian mechanical motion via single and multi-phonon subtraction from a thermal state
• Self-learning Machines based on Hamiltonian Echo Backpropagation
• Analytical approach of Brillouin Amplification over threshold
• Second-Order Coherence Across the Brillouin Lasing Threshold
• RF-Photonic Deep Learning Processor with Shannon-Limited Data Movement

Cited by in corpus (2)

• Passive All-Optical Nonlinear Neuron Activation via PPLN Nanophotonic Waveguides
• Giant Brillouin gain in frozen CS2 capillaries