Stability of an Optical Neural Network Trained by the Maximum-Likelihood Algorithm

IF 1 Q4 OPTICS

Optical Memory and Neural Networks Pub Date : 2024-01-30 DOI:10.3103/s1060992x2307010x

B. V. Kryzhanovsky, V. I. Egorov

引用次数: 0

Abstract

The possibility of the maximum-likelihood algorithm-based deep learning of an optical neural network is considered. Using the optimization of thermodynamic parameters of the network, the algorithm can fail when the network undergoes a phase transition caused by changes of network weights in learning. The approach based on Schraudolph–Kamenetsky [1] and Karandashev–Malsagov [2] algorithms is used in computer simulation. Both algorithms allow the free energy of the system on a planar graph to be computed exactly. The restrictions on the number of negative connections are determined that secure the stability of the system, the absence of the phase transition and unrestrained use of the maximum-likelihood algorithm.

Abstract Image

查看原文本刊更多论文

用最大似然算法训练的光学神经网络的稳定性

摘要研究了基于最大似然算法的光神经网络深度学习的可能性。利用网络热力学参数的优化，当网络在学习过程中因网络权重变化而发生相变时，算法可能会失效。计算机模拟中使用了基于 Schraudolph-Kamenetsky [1] 和 Karandashev-Malsagov [2] 算法的方法。这两种算法都能精确计算平面图上系统的自由能。对负连接数的限制是为了确保系统的稳定性、不出现相变和不受限制地使用最大似然算法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Optical Memory and Neural Networks OPTICS-

CiteScore

1.50

自引率

11.10%

发文量

期刊介绍： The journal covers a wide range of issues in information optics such as optical memory, mechanisms for optical data recording and processing, photosensitive materials, optical, optoelectronic and holographic nanostructures, and many other related topics. Papers on memory systems using holographic and biological structures and concepts of brain operation are also included. The journal pays particular attention to research in the field of neural net systems that may lead to a new generation of computional technologies by endowing them with intelligence.