基于量子计算多Agent的人工神经网络训练方法

A Novel Artificial Neural Network Training Method Based on Quantum Computational Multi-Agent

人工神经网络是可用于建模和求解各种复杂非线性现象的工具。针对传统神经网络训练时间长、节点数目受计算机能力限制等缺点,提出了一种新的多Agent系统理论(MAS)和量子算法的人工神经网络。在人工神经网络训练方法中,每个神经元或节点是一个量子Agent,通过强化学习算法后具有学习能力,然后用QCMAS强化学习算法作为新的神经网络的学习规则。这种新的人工神经网络法具有很好的并行工作能力而且训练时间比经典算法短,实验结果证明了方法的有效性。

Artificial Neural Networks are powerful tools that can be used to model and investigate various complex and non-linear phenomena.In this study,we constructed a new ANN based on Multi-Agent System（MAS） theory and quantum computing algorithm.All nodes in this new ANN were presented as Quantum Computational（QC） agents,and these agents have learning ability.A novel ANN training method was proposed via implementing QCMAS reinforcement learning.This new ANN has powerful parallel-work ability and its training time is shorter than classic algorithm.Experiment results show that this method is effective.