A multilayer recurrent neural network is proposed for solving continuous-time algebraic matrix Riccati equations in real time. The proposed recurrent neural network consists of four bidirectionally connected layers. Each layer consists of an array of neurons. The proposed recurrent neural network is shown to be capable of solving algebraic Riccati equations and synthesizing linear-quadratic con...

This paper outlines the application of Evolving Fuzzy Neural Networks (EFuNN) for the detection of browning in Braebrun apples when in Controlled Atmosphere (CA) storage. Wavelet coef£cients are extracted from each image and these features used to train both an EFuNN and a Multi Layer Perceptron (MLP). We compare the obtained results between these two neural network architectures and found that...

This paper proposes a direct adaptive backstepping control scheme for a class of multi-input-multioutput nonlinear uncertain non-affine systems using output recurrent wavelet neural networks (ORWNNs), called DABCORWNN. The proposed ORWNN combines the advantages of wavelet-based neural network, fuzzy neural network (FNN), and output feedback layer. For the tracking of nonlinear non-affine system...

In order to overcome weaknesses of the conventional crisp neural network and the fuzzy-operation-oriented neural network, we have developed a general fuzzy-reasoning-oriented fuzzy neural network called a Crisp-Fuzzy Neural Network (CFNN) which is capable of extracting high-level knowledge such as fuzzy IF-THEN rules from either crisp data or fuzzy data. A CFNN can eeectively compress a 5 5 fuz...

This paper proposes ajuzzy neural expert system (FNES) with the following two functions: (1) Generalization of the information derived from the training data and embodiment of knowledge in the form of the fuzzy neural network; (2) Extraction of fuzzy If-Then rules with linguistic relative importance of each proposition in an antecedent (I f -part) from a trained neural network. This paper also ...

This paper proposes ajuzzy neural expert system (FNES) with the following two functions: (1) Generalization of the information derived from the training data and embodiment of knowledge in the form of the fuzzy neural network; (2) Extraction of fuzzy If-Then rules with linguistic relative importance of each proposition in an antecedent (I f -part) from a trained neural network. This paper also ...

In an earlier companion paper [56] a supervised learning neural network pattern classifier called the fuzzy min-max classification neural network was described. In this sequel, the unsupervised learning pattern clustering sibling called the fuzzy min-max clustering neural network is presented. Pattern clusters are implemented here as fuzzy sets using a membership function with a hyperbox core t...