• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2018-2020
• /
• 2001

In this study, a Neuro-Fuzzy Controller which has the characteristic of Fuzzy control and Artificial Neural Network is designed. A fuzzy rule to be applied is automatically selected by the allocated neurons. The neurons correspond to Fuzzy rules are created by an expert. To adapt the more precise modeling is implemented by error back propagation learning of adjusting the link-weight of fuzzy membership function in the Neuro-Fuzzy controller. The more classified fuzzy rule is used to include the property of dual mode method. In order to verify the effectiveness of an algorithm designed above, an operating characteristic of a AC servo motor is investigated.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.4
• /
• pp.60-68
• /
• 1994

In this paper we propose a new Hybrid learning rule applied to multilayer feedforward neural networks, which is constructed by combining Hebbian learning rule that is a good feature extractor and Back-Propagation(BP) learning rule that is an excellent classifier. Unlike the BP rule used in multi-layer perceptron(MLP), the proposed Hybrid learning rule is used for uptate of all connection weights except for output connection weigths becase the Hebbian learning in output layer does not guarantee learning convergence. To evaluate the performance, the proposed hybrid rule is applied to classifier problems in two dimensional space and shows better performance than the one applied only by the BP rule. In terms of learning speed the proposed rule converges faster than the conventional BP. For example, the learning of the proposed Hybrid can be done in 2/10 of the iterations that are required for BP, while the recognition rate of the proposed Hybrid is improved by about $0.778\%$ at the peak.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.11
• /
• pp.120-129
• /
• 1992

In this paper we propose a fuzzy-neural network(FNN) which includes both advantages of the fuzzy logic and the neural network. The basic idea of the FNN is to realize the fuzzy rule-base and the process of reasoning by neural network and to make the corresponding parameters be expressed by the connection weights of neural network. After constructing the FNN, a novel controller consisting of a conventional P-controller and a FNN is explained. In this control scheme, the rule-base of a FNN are automatically generated by error back-propagation algorithm. Also the parallel connection of the P-controller and the FNN can guarantee the stability of a plant at initial stage before the rules are completely created. Finally the effectiveness of the proposed strategy will be verified by computer simulations using a 2 degree of freedom robot manipulator.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.2
• /
• pp.224-233
• /
• 1991

The multilayer expanson of single layer NN (Neural Network) was needed to solve the linear seperability problem as shown by the classic example using the XOR function. The EBP (Error Back Propagation ) learning rule is often used in multilayer Neural Networks, but it is not without its faults: 1)D.Rimmelhart expanded the Delta Rule but there is a problem in obtaining Ca from the linear combination of the Weight matrix N between the hidden layer and the output layer and H, wich is the result of another linear combination between the input pattern and the Weight matrix M between the input layer and the hidden layer. 2) Even if using the difference between Ca and Da to adjust the values of the Weight matrix N between the hidden layer and the output layer may be valid is correct, but using the same value to adjust the Weight matrixd M between the input layer and the hidden layer is wrong. Recognitron III was proposed to solve these faults. According to simulation results, since Recognitron III does not learn the three layer NN itself, but divides it into several single layer NNs and learns these with learning patterns, the learning time is 32.5 to 72.2 time faster than EBP NN one. The number of patterns learned in a EBP NN with n input and output cells and n+1 hidden cells are 2**n, but n in Recognitron III of the same size. [5] In the case of pattern generalization, however, EBP NN is less than Recognitron III.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.3
• /
• pp.188-193
• /
• 2000

This paper presents an approach to obtain a reduced neuro-fuzzy model for a plant. The Neuro-Fuzzy Network are compose of the Radial Basis Function Networks with Gausis membership and learned by using temporal back propagation. The dependency in rough set theory is used to eliminate rules. Dependency between the condition membership value of each rule in a model and the output of the plant can allow us to see how much contribution the rule is to identify the plant. While the reduced model maintains the same performance as the original one, the selection algorithm can minimize its complexity and redundancy of the structure.

• Korean Journal of Cognitive Science
• /
• v.13 no.1
• /
• pp.13-21
• /
• 2002

Fuzzy logic ignores some information in the reasoning process. Neural network is powerful tools for the pattern processing, but, not appropriate for the logical reasoning. To model human knowledge, besides pattern processing capability, the logical reasoning capability is equally important. Another new neural network called neural logic network is able to do the logical reasoning. Because the fuzzy inference is a fuzzy logical reasoning, we construct fuzzy inference network based on the neural logic network, extending the existing rule-inference network. And the traditional propagation rule is modified. Experiments are performed to compare search costs by sequential searching and searching by priority. The experimental results show that the searching by priority is more efficient than the sequential searching as the size of the fuzzy inference network becomes larder and an the number of searching increases.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.36-39
• /
• 1996

This paper proposes identification and control algorithm of nonlinear systems and the proposed fuzzy-neural network has following characteristics. The network is roughly divided into premise and consequence. The consequence function is nonlinear function which consists of three parameters and the membership function in the premise contains of two parameters. The parameters in premise and consequence are learned by the extended back-propagation algorithm which has a modified form of the generalized delta rule. Simulation results on the identification show that this method is more effective than that of Narendra [3]. The indirect fuzzy-neural control is made of the fuzzy-neural identification and controller. Result on the indirect fuzzy-neural control shows that the proposed fuzzy-neural network can be efficiently applied to nonlinear systems.

• Journal of Industrial Technology
• /
• v.17
• /
• pp.323-330
• /
• 1997

In this paper, a new approach to modeling of nonlinear systems using fuzzy theory is presented. To express the various and complex behavior of nonlinear system, we combine multiple model method with hierachical prioritized structure, and the mountain clustering technique is used in partitioning of system. TSK rule structure is adopted to form the fuzzy rules, and Back propagation algorithm is used for learning parameters in consequent parts of the rules. Also we soften the paradigm of Mamdani's inference mechanism by using Yager's S-OWA operators. Computer simulations are performed to verify the effectiveness of the proposed method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.2
• /
• pp.128-136
• /
• 1991

A neural network of multi layer perception type, learned by error back propagation learning rule, is generally used for the verification or clustering of similar type of patterns. When learning is completed, the network has a constant value of output depending on a pattern. This paper shows that the intensity of neuron's out put can be controlled by a function which intensifies the excitatory interconnection coefficients or the inhibitory one between neurons in output layer and those in hidden layer. In this paper the value of factor in the function to control the output is derived from the know values of the neural network after learning is completed And also this paper show that the amount of an increased neuron's output in output layer by arbitary value of the factor is derived. For the applications increased recognition performance of a pattern than has distortion is introduced and the output of partially damaged neurons are first managed and this paper shows that the reduced recognition performance can be recovered.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.5
• /
• pp.482-494
• /
• 1992

In this paper, the neuro-fuzzy inferene system for the effective object recognition is studied. The proposed neuro-fuzzy inference system combines learning capability of neural network with inference process of fuzzy theory, and the system executes the fuzzy inference by neural network automatically. The proposed system consists of the antecedence neural network, the consequent neural network, and the fuzzy operational part, For dissolving the ambiguity of recognition due to input variance in the neuro-fuzzy inference system, the antecedence’s fuzzy proposition of the inference rules are automatically produced by error back propagation learining rule. Therefore, when the fuzzy inference is made, the shape of membership functions os adaptively modified according to the variation. The antecedence neural netwerk constructs a separated MNN(Model Classification Neural Network)and LNN(Line segment Classification Neural Networks)for dissolving the degradation of recognition rate. The antecedence neural network can overcome the limitation of boundary decisoion characteristics of nrural network due to the similarity of extracted features. The increased recognition rate is gained by the consequent neural network which is designed to learn inference rules for the effective system output.