Abstract

This paper proposes a new model of a neural network-pseudo-optical neural networks (PONNs), consisting of interfering neurons whose potential varies as a result of the interference of the input periodic signals. The phase differences of the signals depend on the bond lengths between the neurons, and therefore the geometry of the network is essential. A class of PONNs is studied that is called the complete rectilinear model. The holographic and other optical effects in such networks are analyzed.

Optical inner-product implementation of neural networks models

P. Lalanne, P. Chavel, and J. Taboury
Appl. Opt. 28(2) 377-385 (1989)

Optical neural network using vector-feature extraction

Yasunori Kuratomi, Akio Takimoto, Koji Akiyama, and Hisahito Ogawa
Appl. Opt. 32(29) 5750-5758 (1993)

Photonic spiking neural networks with event-driven femtojoule optoelectronic neurons based on Izhikevich-inspired model

Yun-Jhu Lee, Mehmet Berkay On, Xian Xiao, Roberto Proietti, and S. J. Ben Yoo
Opt. Express 30(11) 19360-19389 (2022)

Optical implementation of an associative neural network model with a stochastic process

Jun Ohta, Shuichi Tai, Masaya Oita, Kenichi Kuroda, Kazuo Kyuma, and Koichi Hamanaka
Appl. Opt. 28(12) 2426-2428 (1989)

On-chip photonic diffractive optical neural network based on a spatial domain electromagnetic propagation model

Tingzhao Fu, Yubin Zang, Honghao Huang, Zhenmin Du, Chengyang Hu, Minghua Chen, Sigang Yang, and Hongwei Chen
Opt. Express 29(20) 31924-31940 (2021)