The results of an investigation of a fuzzy logic model for short term load forecasting are presented. The proposed methodology uses fuzzy rules to incorporate historical weather and load data. These fuzzy rules are ob...
详细信息
The results of an investigation of a fuzzy logic model for short term load forecasting are presented. The proposed methodology uses fuzzy rules to incorporate historical weather and load data. These fuzzy rules are obtained from the historical data using a learning-type algorithm. Test results from daily peak and total load forecasts for one year of data from a large scale power system indicate that the fuzzy rule bases can produce results similar in accuracy to more complicated statistical and back-propagation neural network methods. Copyright (C) 1996 Elsevier Science Ltd.
A new constructive algorithm for designing and training multilayer perceptrons is proposed. This algorithm involves the optimization of an objective function for internal representations, which does not require any co...
详细信息
A new constructive algorithm for designing and training multilayer perceptrons is proposed. This algorithm involves the optimization of an objective function for internal representations, which does not require any computation of the network's outputs. Coupled with a strategy for recruiting units during the learning process, this concept provides a scheme for training a multilayer network layer by layer, until self-encoding of the pattern categories is achieved in the final, highest-level representations. Two objective functions are proposed For discrimination problems, recent experimental and theoretical results concerning back-propagation training of networks with one hidden layer and linear outputs suggest the introduction of a particular measure of class separability. For problems involving the approximation of a continuous function, we show that the minimization of the mean squared output error can be achieved by maximizing a statistical measure (the sample coefficient of multiple determination) in the last hidden layer. Simulations are used to illustrate the process of network construction, and to demonstrate the improvements brought by this approach over back-propagation in terms of performance and robustness.
''Package Flow Model'' (PFM) is a simple simulation model for intuitive understanding of various types of system dynamics. In the previous papers, the PFM was proposed and its application to the dynami...
详细信息
''Package Flow Model'' (PFM) is a simple simulation model for intuitive understanding of various types of system dynamics. In the previous papers, the PFM was proposed and its application to the dynamic analysis of nuclear reactor systems was presented. In the present paper, the same model and same application are considered but a new representation method of the PFMs by a neural network is introduced, so that the dynamic simulation of the reactor subsystem can be performed through the calculation of corresponding neural network. Furthermore, the quasi optimum parameter values of each PFM are easily obtained by applying appropriate learning algorithm to get weight-values of the neural network. Some case studies show that the learning process and the obtained optimum values can give us new useful information on approximate understanding of the dynamic behavior of actual processes in the system.
The brain stores various kinds of temporal sequences as long-term memories, such as motor sequences, episodes, and melodies. The present study aims at clarifying the general principle underlying such memories. For thi...
详细信息
The brain stores various kinds of temporal sequences as long-term memories, such as motor sequences, episodes, and melodies. The present study aims at clarifying the general principle underlying such memories. For this purpose, the memory mechanism of sequential patterns is examined from the viewpoint of computational theory and neural network modeling, and a neural network model of sequential pattern memory based on a simple and reasonable principle is presented. Specifically, spatio-temporal patterns varying gradually with time are stably stored in a network consisting of pairs of excitatory and inhibitory cells with recurrent connections;such a pair can achieve non-monotonic input-output characteristics which are essential for smooth sequential recall. Storage is performed using a simple learning algorithm which is based on the covariance rule and requires only that the sequence be input several times and retrieval is highly tolerant to noise. It is thought that a similar principle is used in cerebral memory systems, and the relevance of this model to the brain is discussed. Also, possible roles of hippocampus and basal ganglia in memorizing sequences are suggested.
This paper describes a approach for the ASIC implementation of a multilayered feedforward neural network. Based on a new learning algorithm (Forward Propagation. algorithm), our system realizes a real full-parallel ar...
详细信息
ISBN:
(纸本)7543909405
This paper describes a approach for the ASIC implementation of a multilayered feedforward neural network. Based on a new learning algorithm (Forward Propagation. algorithm), our system realizes a real full-parallel architecture and allows all of the neurons work parallelly and independently. Hardware cost is greatly reduced and the network is easy to expand. The current results of our implementation using Xinlinx FPGA chip is also presented.
In this paper, the hysteresis characterization in fuzzy spaces is presented by utilizing a fuzzy learning algorithm to generate fuzzy rules automatically from numerical data. The hysteresis phenomenon is first describ...
详细信息
In this paper, the hysteresis characterization in fuzzy spaces is presented by utilizing a fuzzy learning algorithm to generate fuzzy rules automatically from numerical data. The hysteresis phenomenon is first described to analyze its underlying mechanism. Then a fuzzy learning algorithm is presented to learn the hysteresis phenomenon and is used for predicting a simple hysteresis phenomenon. The results of learning are illustrated by mesh plots and input-output relation plots. Furthermore, the dependency of prediction accuracy on the number of fuzzy sets is studied. The method provides a useful tool to model the hysteresis phenomenon in fuzzy spaces.
In this paper, a middle-mapping learning algorithm for cellular associative memories is *** algorithm makes full use of the properties of the cellular neural network so that the associative memory has some advantages ...
详细信息
In this paper, a middle-mapping learning algorithm for cellular associative memories is *** algorithm makes full use of the properties of the cellular neural network so that the associative memory has some advantages compared with the memory designed by the outer product method. It can guarantee each prototype is stored-at an equilibrium point. In the practical implementation, it is easy to build up the circuit because the weight matrix presenting the connection between cells is not symmetric. The synchronous updating rule makes its associative speed very fast compared to the Hopfield associative memory.
This paper proposes a fast learning algorithm of neural networks and evaluates the performances of adaptive equalizers using neural networks trained by the proposed algorithm in a frequency-selective fading channel. T...
详细信息
This paper proposes a fast learning algorithm of neural networks and evaluates the performances of adaptive equalizers using neural networks trained by the proposed algorithm in a frequency-selective fading channel. The backpropagation (BP) algorithm which is used widely to train neural networks has a slow convergence rate because it is based on the gradient descent method. This paper presents a fast learning algorithm using the recursive least squares (RLS) algorithm which has a fast convergence rate as an adaptive algorithm for adaptive linear filters. In the proposed algorithm, the sum of the squared error between the actual total input and the desired total input is used as the cost function to apply the RLS algorithm. A simulation result on the exclusive-OR problem indicates that the proposed algorithm is about 8.8 times faster than the BP for the number of iterations required to converge. Recently, there has been interest in adaptive equalizers as an application field of neural networks. However, the performance of an adaptive equalizer using a neural network in a frequency-selective fading channel which is observed in land mobile communications has never been evaluated. Therefore, in this paper, the performances of adaptive equalizers using neural networks trained by the proposed algorithm in a frequency-selective fading channel are evaluated. Especially, an adaptive equalizer using the selectively unsupervised learning neural network proposed by the authors is considered. The adaptive equalizer can reject the false learning by carrying out learning selectively. It is shown that the adaptive equalizer is superior to the conventional one and the one using the conventional neural network.
Refining is an important process in pulping and paper-making industry. With both large uncertainties and rapid response, it is difficult to get accurate models of refining process. Developing efficient and practical c...
详细信息
Refining is an important process in pulping and paper-making industry. With both large uncertainties and rapid response, it is difficult to get accurate models of refining process. Developing efficient and practical control algorithms with robustness and adaptiveness for such a specific process is of essential benefit. In this paper, a hybrid controller is designed and implemented for "refining process optimal control system". It is demonstrated that the hybrid controller gives good performance. Nevertheless, It is very simple and available for practice.
This paper describes a set of efficient learning algorithms for recurrent neural networks (RNN) to facilitate the nonlinear modelling of mechanical systems. These learning algorithms are based on the quasi-Newton meth...
详细信息
This paper describes a set of efficient learning algorithms for recurrent neural networks (RNN) to facilitate the nonlinear modelling of mechanical systems. These learning algorithms are based on the quasi-Newton methods that estimate the inverse Hessian of an objective function from the gradient to enable Newton-like optimization algorithms. The simulation results with two Boolean functions indicate that the new algorithms based on the classical quasi-Newton methods are about two orders of magnitude faster than the steepest descent method. Furthermore, the learning algorithms based on the quasi-Newton with initial scaling and self-scaling are even more efficient than the classical quasi-Newton methods. For instance, the self-scaling method is three orders of magnitude faster than the steepest descent method. To validate the usefulness of the RNNs in nonlinear mechanical system modelling, RNNs are trained to emulate the step response of a robot arm and identify an adequate model of a 20 HP screw compressor from its operating data.
暂无评论