Efficient training and design of photonic neural network through neuroevolution

Abstract

Recently, optical neural networks (ONNs) integrated in photonic chips has received extensive attention because they are expected to implement the same pattern recognition tasks in the electronic platforms with high efficiency and low power consumption. However, the current lack of various learning algorithms to train the ONNs obstructs their further development. In this article, we propose a novel learning strategy based on neuroevolution to design and train the ONNs. Two typical neuroevolution algorithms are used to determine the hyper-parameters of the ONNs and to optimize the weights (phase shifters) in the connections. In order to demonstrate the effectiveness of the training algorithms, the trained ONNs are applied in the classification tasks for iris plants dataset, wine recognition dataset and modulation formats recognition. The calculated results exhibit that the training algorithms based on neuroevolution are competitive with other traditional learning algorithms on both accuracy and stability. Compared with previous works, we introduce an efficient training method for the ONNs and demonstrate their broad application prospects in pattern recognition, reinforcement learning and so on.

arXiv comment11 pages, 4 figures

References in corpus (10)

• Deep Learning in Neural Networks: An Overview
• Deep Learning with Coherent Nanophotonic Circuits
• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Outlook for inverse design in nanophotonics
• Deep Learning in Spiking Neural Networks
• Training of photonic neural networks through in situ backpropagation
• Reinforcement Learning in a large scale photonic Recurrent Neural Network
• Design of optical neural networks with component imprecisions
• A CMOS Spiking Neuron for Brain-Inspired Neural Networks with Resistive Synapses and In-Situ Learning
• Efficient spectrum prediction and inverse design for plasmonic waveguide systems based on artificial neural networks

Cited by in corpus (5)

• Machine learning and evolutionary algorithm studies of graphene metamaterials for optimized plasmon-induced transparency
• Asymmetrical estimator for training encapsulated deep photonic neural networks
• Hardware-Efficient Photonic Tensor Core: Accelerating Deep Neural Networks with Structured Compression
• Optical neural network architecture for deep learning with the temporal synthetic dimension
• Emergence of biased errors in imperfect photonic circuits