Application of a cascade BAM neural expert system to conceptual design for facility layout

The major contribution of this novel application is the pilot development and feasibility study for a bank of cascade BAM (Bidirectional Associative Memories) neural networks. This improved BAM structure functions as an expert system for conceptual facility layout or for preliminary construction layout design. This application, rather than being a better analytical algorithm or a better production expert system, builds a neural expert system with the capability of incrementally learning layout design examples for a given set of constraints. The cascade BAM incremental learning methodology, which distinguishes this system from the more frequently used Backpropagation Network (BPN) learning system, creates effective multibidirectional generalization behavior from qualitative, goal-driven layout design experience. The initial tests of learnability are presented by its applicability to conceptual layout design problems, and their solutions are assessed and compared with the learning ability of a standard BAM. Issues deserving further investigation are addressed as well.     

基于神经网络结构学习的知识求精方法

知识求精是知识获取中必不可少的步骤．已有的用于知识求精的ＫＢＡＮＮ（ｋｎｏｗ ｌｅｄｇｅ ｂａｓｅｄ ａｒｔｉｆｉｃｉａｌｎｅｕｒａｌｎｅｔｗ ｏｒｋ）方法,主要局限性是训练时不能改变网络的拓扑结构．文中提出了一种基于神经网络结构学习的知识求精方法,首先将一组规则集转化为初始神经网络,然后用训练样本和结构学习算法训练初始神经网络,并提取求精的规则知识．网络拓扑结构的改变是通过训练时采用基于动态增加隐含节点和网络删除的结构学习算法实现的．大量实例表明该方法是有效的     

一种基于神经网络的知识获取方法研究与应用

提出了一种基于神经网络的知识获取方法,该方法利用语言神经元,对具有开区域的连续输入变量,自动产生相应的语言变量输出,讨论了相应的神经网络训练和知识获取方法,所获取的知识以If-Then的规则形式表示,具有简洁、紧凑、不必进一步化简、易于理解等特点,并给出一个在教学型专家系统中获取专家领域知识的应用实例。     

Computer networks design using hybrid fuzzy expert systems

 Designing and configuring large computer networks to support a variety of applications and computational environments is difficult, as it not only requires highly specialized technical skills and knowledge, but also a deep understanding of a dynamic commercial market. Hybrid fuzzy expert systems integrate fuzzy expert systems and neural networks methods replacing classical hard decision methods and providing better performance than traditional techniques. In this paper, we present an integrated fuzzy expert system, machine learning, and neural networks approach to large structured computer networks design and evaluation. After presenting an overview of the system and the major research choices, we describe in detail the system's modules and present examples of its potential use.     

采用规则与人工神经网络表示知识的专家系统

本文描述了采用规则与人工神经网络表示知识的专家系统,一种前向式神经网络模型及其学习算法,表明采用多种形式表示知识有利于提高系统的灵活性和有效性。     

Knowledge Incorporation into Neural Networks From Fuzzy Rules

The incorporation of prior knowledge into neural networks can improve neural network learning in several respects, for example, a faster learning speed and better generalization ability. However, neural network learning is data driven and there is no general way to exploit knowledge which is not in the form of data input-output pairs. In this paper, we propose two approaches for incorporating knowledge into neural networks from fuzzy rules. These fuzzy rules are generated based on expert knowledge or intuition. In the first approach, information from the derivative of the fuzzy system is used to regularize the neural network learning, whereas in the second approach the fuzzy rules are used as a catalyst. Simulation studies show that both approaches increase the learning speed significantly.     

基于神经网络的知识获取

本文提出了用基于规则专家系统与神经网络的集成，该系统实现了从实例中自动获取知识的功能．在产生和控制不完全情况方面提高了专家系统的推理能力．它使用无导师学习算法的神经网络来获取正规数据，并用一个符号生成器把这些正规的数据变换成规则．生成规则和训练后的神经网络作为知识库嵌于专家系统中．在诊断阶段，为了诊断不明情况，可同时使用知识库和人类专家的知识，而且系统可以利用训练过的神经网络的综合能力进行诊断，并使不相符数据完整化．     

A generic fuzzy aggregation operator: rules extraction from and insertion into artificial neural networks

Multilayered feedforward artificial neural networks (ANNs) are black boxes. Several methods have been published to extract a fuzzy system from a network, where the input–output mapping of the fuzzy system is equivalent to the mapping of the ANN. These methods are generalized by means of a new fuzzy aggregation operator. It is defined by using the activation function of a network. This fact lets to choose among several standard aggregation operators. A method to extract fuzzy rules from ANNs is presented by using this new operator. The insertion of fuzzy knowledge with linguistic hedges into an ANN is also defined thanks to this operator.     

Cascade ARTMAP: integrating neural computation and symbolic knowledge processing

This paper introduces a hybrid system termed cascade adaptive resonance theory mapping (ARTMAP) that incorporates symbolic knowledge into neural-network learning and recognition. Cascade ARTMAP, a generalization of fuzzy ARTMAP, represents intermediate attributes and rule cascades of rule-based knowledge explicitly and performs multistep inferencing. A rule insertion algorithm translates if-then symbolic rules into cascade ARTMAP architecture. Besides that initializing networks with prior knowledge can improve predictive accuracy and learning efficiency, the inserted symbolic knowledge can be refined and enhanced by the cascade ARTMAP learning algorithm. By preserving symbolic rule form during learning, the rules extracted from cascade ARTMAP can be compared directly with the originally inserted rules. Simulations on an animal identification problem indicate that a priori symbolic knowledge always improves system performance, especially with a small training set. Benchmark study on a DNA promoter recognition problem shows that with the added advantage of fast learning, cascade ARTMAP rule insertion and refinement algorithms produce performance superior to those of other machine learning systems and an alternative hybrid system known as knowledge-based artificial neural network (KBANN). Also, the rules extracted from cascade ARTMAP are more accurate and much cleaner than the NofM rules extracted from KBANN.     

基于神经网络和规则的专家系统的应用研究

本文对专家系统在材料加工领域的应用特点及现状进行了分析与研究，采用基于人工神经网络和规则的知识表示和获取方法，实现了一个混合型的专家系统；并结合实例，讨论了神经网络与专家系统的集成，以及系统的程序框架与功能设计、各模块的主要实现思路；最后，通过实验数据验证，系统的泛化结果误差小于6％。