基于梯度的并行协作模块化神经网络体系结构

该文提出了一种基于梯度的并行协作模块化神经网络的体系结构(GPCMNN)．它通过分解模块,根据梯度方法对学习样本空间自动分解,由子空间识别模块和子任务模块实现各子样本空间的识别和学习,集成模块将子样本空间结果集成得系统的输出,实现了复杂任务的自动分解、判定和模块化训练策略．实验表明,该文提出的GPCMNN体系结构是可行的、有效的;与非模块化神经网络技术相比,提高了训练速度,改善了网络性能．它具有高效并行的运行效率、便于硬件实现等特点,同时又保持了PCMNN算法的优点,改进了它的不足．     

一种能简化复杂分类问题的矩阵模块神经网络分类器

主要针对大训练集和类别非对称训练集等复杂分类问题提出一种基于新的任务分解技术的矩阵模块神经网络分类系统,它将一个复杂分类任务分解为多个简单的子任务来解决,每个子任务只是在两个子空间内进行,且由一个具有简单结构的神经网络模块来完成;所有网络模块将组成一个神经网络矩阵,最终将该神经网络矩阵的输出矩阵集成得到最终分类结果.本文通过理论分析和模拟实验证明,该矩阵模块神经网络能节省神经网络的学习时间,提高泛化能力和分类精度.     

Fuzzy Neural Network Models for Classification

In this paper, we combine neural networks with fuzzy logic techniques. We propose a fuzzy-neural network model for pattern recognition. The model consists of three layers. The first layer is an input layer. The second layer maps input features to the corresponding fuzzy membership values, and the third layer implements the inference engine. The learning process consists of two phases. During the first phase weights between the last two layers are updated using the gradient descent procedure, and during the second phase membership functions are updated or tuned. As an illustration the model is used to classify samples from a multispectral satellite image, a data set representing fruits, and Iris data set.     

模块化神经网络MATLAB仿真系统的研制

分析了模块化神经网络MATLAB仿真系统的设计和实现。该仿真系统充分运用MATLAB对数值计算、图形处理的强大功能，采用可扩展的图形用户界面，开发了一套适合模块化神经网络试验和研究平台。介绍了模块化神经网络（MNN）的子网动态集成方法，并提出了一种基于“一专多能”思想的集成训练方法。该仿真系统将算法、数据、仿真演示有机集成，为后期的设计开发提供了有力的支持。     

Bayesian Network Classifiers

Recent work in supervised learning has shown that a surprisingly simple Bayesian classifier with strong assumptions of independence among features, called naive Bayes, is competitive with state-of-the-art classifiers such as C4.5. This fact raises the question of whether a classifier with less restrictive assumptions can perform even better. In this paper we evaluate approaches for inducing classifiers from data, based on the theory of learning Bayesian networks. These networks are factored representations of probability distributions that generalize the naive Bayesian classifier and explicitly represent statements about independence. Among these approaches we single out a method we call Tree Augmented Naive Bayes (TAN), which outperforms naive Bayes, yet at the same time maintains the computational simplicity (no search involved) and robustness that characterize naive Bayes. We experimentally tested these approaches, using problems from the University of California at Irvine repository, and compared them to C4.5, naive Bayes, and wrapper methods for feature selection.     

基于模块化神经网络的T细胞表位预测

文章提出了一种应用于T细胞表位预测的模块化神经网络,这种神经网络先用一个过滤模块将不可结合的蛋白质序列过滤掉,然后将可结合的蛋白质输入到各个分类模块中进行训练学习,最后根据三个分类模块的结果进行最大值判定输出最后结果。实验结果证明,用这种模块化神经网络结构对T细胞表位进行预测比单个BP神经网络具有更高的准确率和数据的自我组织及学习能力。     

MIGA, A Software Tool for Nonlinear System Modelling with Modular Neural Networks

This paper presents a software tool suitable for dynamic system modelling. The models generated by this tool are modular neural networks, see [1]. Each module behaves like a functional block and is connected to the other modules like in classical block diagrams. This tool allows the inclusion of a priori knowledge and, furthermore, to extract physical information from the models, once the system has learned. The modelling tool is capable of automatic model generation, parameter estimation and model validation.     

Using a Neural Network to Approximate an Ensemble of Classifiers

Several methods (e.g., Bagging, Boosting) of constructing and combining an ensemble of classifiers have recently been shown capable of improving accuracy of a class of commonly used classifiers (e.g., decision trees, neural networks). The accuracy gain achieved, however, is at the expense of a higher requirement for storage and computation. This storage and computation overhead can decrease the utility of these methods when applied to real-world situations. In this Letter, we propose a learning approach which allows a single neural network to approximate a given ensemble of classifiers. Experiments on a large number of real-world data sets show that this approach can substantially save storage and computation while still maintaining accuracy similar to that of the entire ensemble.     

基于粗糙集的并行协作模块化神经网络模式分类器

该文提出了基于粗糙集的K类模式分类器的体系结构(RSPCMNNC),基于粗糙集理论提出了三个预处理算法,简化了分类器的结构,降低了学习难度,有效地避免产生过多的子网。样本空间基于最大均衡的策略来划分,保证BP算法在学习过程中的有效性。实验结果表明,该文提出的RSPCMNNC分类器显示出更高的识别率,对于实际应用中多特征模式的识别问题,具有很大的实用价值。     

软组合概率神经网络分类器人脸识别方法

概率神经网络分类器具有学习速度快、易于实现的特点,而且其输出是后验概率, 使得分类器的软组合变得容易。利用概率神经网络的这些特点,提出了软组合概率神经网络分类器人脸识别方法,该方法包括3步:(1)对人脸图像做不完全小波包分解;(2)用包含低频成分的小波子空间图像训练概率神经网络分类器;(3)用模糊积分组合训练好的分类器。将该方法与3种基于矩阵子空间的人脸识别方法在JAFFE、YALE、ORL和FERET 4个人脸数据库上进行了实验比较,结果表明,提出的方法在识别精度和CPU时间两方面均优于其他3种方法。     

数值优化改进的BP网络的模式分类对比

研究了共轭梯度算法、拟牛顿算法、LM算法三类常用的数值优化改进算法,基于这三类数值优化算法分别对BP神经网络进行改进,并构建了相应的BP神经网络分类模型,将构建的分类模型应用于二维向量模式的分类,并进行了泛化能力测试,将不同BP网络分类模型的分类结果进行对比. 仿真结果表明,对于中小规模的网络而言,LM数值优化算法改进的BP网络的分类结果最为精确,收敛速度最快,分类性能最优;共轭梯度数值优化算法改进的BP网络的分类结果误差最大,收敛速度最慢,分类性能最差;拟牛顿数值优化算法改进的BP网络的分类结果误差值、收敛速度及分类性能介于上述两种算法之间.     

基于类脑模块化神经网络的污水处理过程关键出水参数软测量

针对城市污水处理过程关键出水参数难以实时检测的问题,文中提出了一种基于类脑模块化神经网络（Brain-like modular neural network,BLMNN）的关键出水参数软测量方法.首先,基于互信息和专家知识进行任务分解,分析关键出水参数的相关变量,获取各出水参数的辅助变量.其次,通过模拟大脑皮层模块化分区结构,构建软测量子模型对各水质参数进行同步测量,降低软测量模型复杂度的同时保证了其精度.最后,通过基于实际数据的仿真实验验证了所提出方法的准确性和有效性.     

CMNN: Cooperative Modular Neural Networks

A new cooperative modular neural network (CMNN) architecture for classification is introduced. The main idea is to decrease partial over- and under-learning by dealing with different levels of overlap in separate modules. Motivated by some basic biological modular-networks’ concepts, CMNN proposes a new cooperation scheme to integrate the information available at its modules. Cooperative modules utilize some voting techniques to come up with a collective decision. Moreover, the specialization concept is proposed as a solution for high overlap regions in the input space. A number of experiments which assess CMNN’s capabilities are outlined. The experiments compare it to several non-modular and modular state-of-the-art alternatives using several benchmark problems. The proposed modularization scheme proves to be an effective way to deal with the complexities of real classification problems.     

一种基于混合建模的模块化神经网络控制方法

针对传统神经网络用于复杂过程系统的控制时难于收敛的问题,文章提出了基于混合建模的模块化的神经网络模型。采取运行机理建模和神经网络建模相结合的方式,把输入样本空间进行划分,实现基于混合专家网络的建模。试验结果表明,对大型燃煤锅炉供热系统,文章提出的方法可以较好地提高供热系统的稳定性和供热质量。     

基于小波神经网络的多属性决策方法及应用

分析了多属性决策问题及现有方法,提出用小波神经网络建立权重分配模型以改进多属性决策的方法,使权重的确定较为客观准确,并具有自学习功能。在工业产品质量决策方案评价中的应用表明了该方法的有效性。     

A Neural Network with Evolutionary Neurons

A neural network, combining evolution and learning is introduced. The novel feature of the proposed network is the evolutionary character of its neurons. The argument of the transfer function performed by the neurons in the network is neither a linear nor polynomial function of the inputs to the neuron, but an unknown general function P(·). The adequate functional form P(·) for each neuron, is achieved during the learning period by means of genetic programming. The proposed neural network is applied to the problem domain of time series prediction of the Mackey-Glass delay differential equation. Simulation results indicate that the new neural network is effective.     

Simulation of Quantification Abilities Using a Modular Neural Network Approach

A novel modular neural network architecture and its application to the field of numerical cognition simulation are presented. Previous modular connectionist systems are typically constrained at one of two levels: at the representational level, in that the connectivity of the modules is hard-wired by the modeller; or at a local architectural level, in that the modeller explicitly allocates each module to a specific subtask. Our approach aims to minimise the constraints, thus reducing the bias possibly introduced by the modeller. The efficacy of this approach is demonstrated through the successful simulation of the development of two quantification abilities, subitising and counting, amongst children. It is concluded that such a minimally constrained modular system may contribute to both the capturing of learnt behaviour, and the allocation of modules to subtasks according to the nature of the task.     

神经网络结构的动态构筑方法

如何决定人工神经网络的适当规模,以往都是通过试探法实现,不但费时,而且无规律可循。文中基于神经网络的基本学习算法,构筑动态网络结构,使之更符合抽取的新的输入、输出特性。讨论了构筑动态神经网络的一种途径。学习是从最简单的网络(无隐含单元)开始,新的单元一步一步补充,直到网络给出一个满意的模拟值。     

Neural and Wavelet Network Models for Financial Distress Classification

This work analyzes the use of linear discriminant models, multi-layer perceptron neural networks and wavelet networks for corporate financial distress prediction. Although simple and easy to interpret, linear models require statistical assumptions that may be unrealistic. Neural networks are able to discriminate patterns that are not linearly separable, but the large number of parameters involved in a neural model often causes generalization problems. Wavelet networks are classification models that implement nonlinear discriminant surfaces as the superposition of dilated and translated versions of a single “mother wavelet” function. In this paper, an algorithm is proposed to select dilation and translation parameters that yield a wavelet network classifier with good parsimony characteristics. The models are compared in a case study involving failed and continuing British firms in the period 1997–2000. Problems associated with over-parameterized neural networks are illustrated and the Optimal Brain Damage pruning technique is employed to obtain a parsimonious neural model. The results, supported by a re-sampling study, show that both neural and wavelet networks may be a valid alternative to classical linear discriminant models.