Results 1  10
of
14
An online selfconstructing neural fuzzy inference network and its applications
 IEEE. Trans. Fuzzy. Sys
, 1998
"... Abstract—A selfconstructing neural fuzzy inference network (SONFIN) with online learning ability is proposed in this paper. The SONFIN is inherently a modified Takagi–Sugeno–Kang (TSK)type fuzzy rulebased model possessing neural network’s learning ability. There are no rules initially in the SO ..."
Abstract

Cited by 92 (21 self)
 Add to MetaCart
Abstract—A selfconstructing neural fuzzy inference network (SONFIN) with online learning ability is proposed in this paper. The SONFIN is inherently a modified Takagi–Sugeno–Kang (TSK)type fuzzy rulebased model possessing neural network’s learning ability. There are no rules initially in the SONFIN. They are created and adapted as online learning proceeds via simultaneous structure and parameter identification. In the structure identification of the precondition part, the input space is partitioned in a flexible way according to a aligned clusteringbased algorithm. As to the structure identification of the consequent part, only a singleton value selected by a clustering method is assigned to each rule initially. Afterwards, some additional significant terms (input variables) selected via a projectionbased correlation measure for each rule will be added to the consequent part (forming a linear equation of input variables) incrementally as learning proceeds. The combined precondition and consequent structure identification scheme can set up an economic and dynamically growing network, a main feature of the SONFIN. In the parameter identification, the consequent parameters are tuned optimally by either least mean squares (LMS) or recursive least squares (RLS) algorithms and the precondition parameters are tuned by backpropagation algorithm. Both the structure and parameter identification are done simultaneously to form a fast learning scheme, which is another feature of the SONFIN. Furthermore, to enhance the knowledge representation ability of the SONFIN, a linear transformation for each input variable can be incorporated into the network so that much fewer rules are needed or higher accuracy can be achieved. Proper linear transformations are also learned dynamically in the parameter identification phase of the SONFIN. To demonstrate the capability of the proposed SONFIN, simulations in different areas including control, communication, and signal processing are done. Effectiveness of the SONFIN is verified from these simulations. Index Terms—Equalizer, noisy speech recognition, projectionbased correlation measure, similarity measure, TSK fuzzy rule.
StructureAdaptable Neurocontrollers: A HardwareFriendly Approach
 In Proceedings of the International WorkConference on Artificial and Natural Neural Networks IWANN97
, 1997
"... . This paper presents a hardwarefriendly approach for adapting the structure of a reinforcement, learningbased neurocontroller. An unsupervised clustering algorithm is used to partition the state space of a system and to adapt the size of its reinforcement module. In the wellknown inverted pendulu ..."
Abstract

Cited by 7 (4 self)
 Add to MetaCart
. This paper presents a hardwarefriendly approach for adapting the structure of a reinforcement, learningbased neurocontroller. An unsupervised clustering algorithm is used to partition the state space of a system and to adapt the size of its reinforcement module. In the wellknown inverted pendulum problem, the system has proven to be much faster than previous neurocontroller approaches. We are currently working on an implementation of the system using fieldprogrammable logic devices. 1 Introduction A major problem in nonlinear control is the tuning and adaptation of the controller. For this purpose a model of the process is usually developed. Then, following an approximation of the inverse relation between the desired outputs and the control actions, the controller is adjusted. However, for many realworld problems there is no available quantitative data regarding inputoutput relations, rendering analytical modeling very difficult [6]; furthermore, errors in the model can lead to...
Zikidis, "NeuroFAST: online neurofuzzy ARTbased structure and parameter learning TSK model
 IEEE Trans. Syst. Man., Cybern
, 2001
"... Abstract—NeuroFAST is an online fuzzy modeling learning algorithm, featuring high function approximation accuracy and fast convergence. It is based on a firstorder Takagi–Sugeno–Kang (TSK) model, where the consequence part of each fuzzy rule is a linear equation. Structure identification is perfor ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
Abstract—NeuroFAST is an online fuzzy modeling learning algorithm, featuring high function approximation accuracy and fast convergence. It is based on a firstorder Takagi–Sugeno–Kang (TSK) model, where the consequence part of each fuzzy rule is a linear equation. Structure identification is performed by a fuzzy adaptive resonance theory (ART)like mechanism, assisted by fuzzy rule splitting and adding procedures. The well known rule continuously performs parameter identification on both premise and consequence parameters. Simulation results indicate the potential of the algorithm. It is worth noting that NeuroFAST achieves a remarkable performance in the Box and Jenkins gas furnace process, outperforming all previous approaches compared. Index Terms — rule, fuzzy ART learning, structure/parameter identification, Takagi–Sugeno–Kang (TSK) fuzzy reasoning model.
Training reinforcement neurocontrollers using the polytope algorithm
 Neural Processing Letters
, 1999
"... Abstract. A new training algorithm is presented for delayed reinforcement learning problems that does not assume the existence of a critic model and employs the polytope optimization algorithm to adjust the weights of the action network so that a simple direct measure of the training performance is ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
(Show Context)
Abstract. A new training algorithm is presented for delayed reinforcement learning problems that does not assume the existence of a critic model and employs the polytope optimization algorithm to adjust the weights of the action network so that a simple direct measure of the training performance is maximized. Experimental results from the application of the method to the pole balancing problem indicate improved training performance compared with criticbased and genetic reinforcement approaches. Key words: reinforcement learning, neurocontrol, optimization, polytope algorithm, pole balancing, genetic reinforcement
FPGA Implementation of a Network of Neuronlike Adaptive Elements
 In Proceedings of the Intl. Conf. on Artificial Neural Networks ICANN97
, 1997
"... . A well known model of reinforcement learning is called Adaptive Heuristic Critic learning. It is composed of two so called "neuronlike adaptive elements" and has been used to solve difficult learning control problems. In this paper we present an FPGA design and implementation of such alg ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
. A well known model of reinforcement learning is called Adaptive Heuristic Critic learning. It is composed of two so called "neuronlike adaptive elements" and has been used to solve difficult learning control problems. In this paper we present an FPGA design and implementation of such algorithm, and, furthermore, we describe a neurocontroller system composed of a network of neuronlike adaptive elements and an unsupervised clustering system called FAST, which dynamically partitions the input state space of the system being controlled. 1 Introduction The Adaptive Heuristic Critic (AHC) algorithm is an early model of reinforcement learning presented by Barto, Sutton, and Anderson in a very influential paper of 1983 entitled "Neuronlike Adaptive Elements That Can Solve Difficult Learning Control Problems" [2]. Such algorithm has proven to be very successful in solving control problems like the wellknown inverted pendulum problem. In this paper we present an FPGA implementation of such a...
SpeedingUp Adaptive Heuristic Critic Learning with FPGABased Unsupervised Clustering
 Proceedings of the IEEE International Conference on Evolutionary Computation
, 1997
"... Neurocontrol is a crucial area of fundamental research within the neural network field. Adaptive Heuristic Critic learning is a key algorithm for real time adaptation in neurocontrollers. In this paper we present how an unsupervised neural network model with adaptable structure can be used to speedu ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Neurocontrol is a crucial area of fundamental research within the neural network field. Adaptive Heuristic Critic learning is a key algorithm for real time adaptation in neurocontrollers. In this paper we present how an unsupervised neural network model with adaptable structure can be used to speedup Adaptive Heuristic Critic learning, its FPGA design, and how it adapts the neurocontroller to the state space of the system being controlled. 1 Introduction Artificial neural networks are massively parallel systems with the capability of infer a response to an unknown situation, achieved through generalizing previous encountered, known situations. The lack of knowledge in determining the appropriate topology of an artificial neural network, limits such capability. Evolutionary techniques (i.e. genetic algorithms) have been widely used for the design of these networks [2]. Essentially, the algorithm employs a population of neural networks, each encoded as a bit string "genome"; evolution p...
Reinforcement Learning Using The Stochastic Fuzzy MinMax Neural Network
 Neural Processing Letters, 13:213–220
, 2001
"... The fuzzy minmax neural network constitutes a neural architecture that is based on hyperbox fuzzy sets and can be incrementally trained by appropriately adjusting the number of hyperboxes and their corresponding volumes. An extension to this network has been proposed recently, that is based on t ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
The fuzzy minmax neural network constitutes a neural architecture that is based on hyperbox fuzzy sets and can be incrementally trained by appropriately adjusting the number of hyperboxes and their corresponding volumes. An extension to this network has been proposed recently, that is based on the notion of random hyperboxes and is suitable for reinforcement learning problems with discrete action space. In this work, we elaborate further on the random hyperbox idea and propose the stochastic fuzzy minmax neural network, where each hyperbox is associated with a stochastic learning automaton. Experimental results using the pole balancing problem indicate that the employment of this model as an action selection network in reinforcement learning schemes leads to superior learning performance compared with the traditional approach where the multilayer perceptron is employed. Keywords: Fuzzy minmax neural network, reinforcement learning, stochastic automaton, pole balancing pro...
PLEASE SCROLL DOWN FOR ARTICLE
, 1997
"... Publication details, including instructions for authors and subscription information: ..."
Abstract
 Add to MetaCart
(Show Context)
Publication details, including instructions for authors and subscription information:
IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS−PART B: CYBERNETICS A Fuzzy Controller with Supervised Learning Assisted Reinforcement Learning Algorithm For Obstacle Avoidance
"... Abstract—Fuzzy logic system promises an efficient way for obstacle avoidance. However, it is difficult to maintain the correctness, consistency and completeness of a fuzzy rule base constructed and tuned by a human expert. Reinforcement Learning method is capable of learning the fuzzy rules automati ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract—Fuzzy logic system promises an efficient way for obstacle avoidance. However, it is difficult to maintain the correctness, consistency and completeness of a fuzzy rule base constructed and tuned by a human expert. Reinforcement Learning method is capable of learning the fuzzy rules automatically. However, it incurs heavy learning phase and may result in an insufficiently learnt rule base due to the curse of dimensionality. In this paper, we propose a neural fuzzy system with mixed coarse learning and fine learning phases. In the first phase, Supervised Learning method is used to determine the membership functions for the input and output variables simultaneously. After sufficient training, fine learning is applied which employs Reinforcement Learning algorithm to finetune the membership functions for the output variables. For sufficient learning, a new learning method using modified Sutton and Barto’s model is proposed to strengthen the exploration. Through this twostep tuning approach, the mobile robot is able to perform collisionfree navigation. To deal with the difficulty in acquiring large amount of training data with high consistency for the Supervised Learning, we develop a Virtual Environment simulator, which is able to provide Desktop Virtual Environment (DVE) and Immersive Virtual Environment (IVE) visualization. Through operating a mobile robot in the Virtual Environment (DVE/IVE) by a skilled human operator, the training data are readily obtained and used to train the neural fuzzy system. Index Terms—fuzzy system, obstacle avoidance, supervised learning, reinforcement learning, virtual environment. I.
Neural Networks PERGAMON
, 1999
"... FasBack neurofuzzy systems www.elsevier.com/locate/neunet ..."
(Show Context)