A modular neural network architecture based on parallel cooperation 并行协作模块化神经网络体系结构
Moreover, various theoretical explanations proposed recently justify the effectiveness of some conventional methods for modular neural network 而且最近所提出的各种理论解释也都证实了一些常用模块化方法的有效性。
In this paper, the first aspect is mainly studied, a scheme of selective ensemble is presented, and a new architecture of modular neural networks is presented 本文的工作主要集中在结论合成方面,提出子网络选择性集成的方案,提出一种新的层次模块化神经网络模型。
modular neural network is a new learning model based on multi-agents, whose decisions are combined in a fashion of competition and cooperation of a number of artificial neural networks 模块化神经网络是一种由多个智能体组成的学习机模型,是由多个神经网络以协作或竞争的方式构建的学习系统。
The research for modular neural network concentrates on two aspects : how to combine the decisions of the component networks, and how to generate the component networks in the entire system 当前,模块化神经网络的研究主要集中在两个方面,即如何将多个神经网络的输出结论进行结合以及如何生成系统中的个体网络。
In chapter 3, problems of adaptive combination are discussed . in chapter 4 a new architecture of multiple neural networks based on modularity is presented, which is named hierarchical modular neural networks 第四章,本文应用分而治之的思想提出了一种层次模块化神经网络新方法?三层结构的模块化神经网络模型,在提高算法性能方面有一定优势。
A great deal of successful applications demonstrates that modular neural network outperforms single neural network in terms of generalization and reliability and undoubtedly provides for us with a new tool for problem-solving 大量的实例研究表明,模块化神经网络在泛化能力和可靠性上比单一神经网络都有所提高,为我们提供了一条问题求解的新途径。
The laboratory has proposed several speaker recognition methods involving computational auditory models, modular neural networks, gaussian mixed models, hidden markov models, and implemented a recognition framework combining semantic and voiceprint information 实验室提出了基于听觉计算模型、模块化神经网络、高斯混合模型、隐马尔科夫模型等说话人识别方法,以及结合语义和声纹信息的说话人识别框架。
At the same time, the robust algorithm of modular neural networks is studied . this paper composes five chapters in all . chapter 1 expatiates the probability and necessity of the generation of modular aeural networks from the viewpoints of commands, neurobiology and social science 第一章,本文首先从需求,神经生理学和社会科学等角度阐述了模块化神经网络出现的可能和必然,然后从理论与应用两个方面介绍了模块化神经网络的研究现状及应用前景。
In chapter 2 a robust learning algorithm of modular neural networks based on the theory of robust regression is presented . empirical study demonstrates that the robust learning algorithm of mnn has better precision and generalization than both modular neural networks and single neural network with the same robust algorithm, when trained under the contained dada 第二章,本文提出了一种模块化神经网络的鲁棒学习算法,实验研究表明模块化神经网络的鲁棒学习算法对于污染样本的学习能获得较好的鲁棒性能和较高的学习精度,特别是在模型较复杂时,该算法的效果尤为明显。