作者:
Verma, BLaboratory of Chromatography
DEPg.Fac.Quimica Universidad Nacional Autonoma de Mexico Circuito interior Cd Universitaria/CP 04510 Mexico D.F.Mexico
Training a multilayer perceptron by an error backpropagation algorithm is slow and uncertain, This paper describes a new approach which is much faster and certain than error backpropagation, The proposed approach is b...
详细信息
Training a multilayer perceptron by an error backpropagation algorithm is slow and uncertain, This paper describes a new approach which is much faster and certain than error backpropagation, The proposed approach is based on combined iterative and direct solution methods, In this approach, we use an inverse transformation for linearization of nonlinear output activation functions, direct solution matrix methods for training the weights of the output layer;and gradient descent, the delta rule, and other proposed techniques for training the weights of the hidden layers, The approach has been implemented and tested on many problems, Experimental results, including training times and recognition accuracy, are given, Generally, the approach achieves accuracy as good as or better than perceptrons trained using error backpropagation, and the training process is much faster than the error backpropagation algorithm and also avoids local minima and paralysis.
This paper presents an extensive study of fault tolerant training of feedforward artificial neural networks. We present several versions of a very robust training algorithm and report the results of their simulations....
详细信息
This paper presents an extensive study of fault tolerant training of feedforward artificial neural networks. We present several versions of a very robust training algorithm and report the results of their simulations. Our algorithm is shown to outperform all existing training algorithms in its ability to tolerate different fault types and larger number of hidden unit failures. We show that the generalization ability of the proposed algorithm is substantially better than that of the standard backpropagation algorithm and is comparable with that of other existing fault tolerant algorithms. The algorithm is based on the backpropagation algorithm with built-in measures for extensive fault tolerant training. A novel concept presented in this paper is that of training the network for fault types beyond the limits of the activation function. We demonstrate that training for such unrealistic fault types enables the network to be more tolerant to realistic fault types within the limits of the activation function. Further, tradeoffs between training time, enhanced fault tolerance, and generalization properties are studied. (C) 1997 Elsevier Science Ltd.
This paper formulates a necessary condition for multilayer nets to have solutions by a set of normal vectors orthogonal to separation hyperplanes. Comparing the necessary condition to the distributions of normal vecto...
详细信息
This paper formulates a necessary condition for multilayer nets to have solutions by a set of normal vectors orthogonal to separation hyperplanes. Comparing the necessary condition to the distributions of normal vectors with the weights and biases initialized ordinarily by random numbers with zero mean, it is derived that bipolar nets are superior to unipolar nets in convergence of the back propagation learning initialized in such an ordinary manner.
A neural network was used to identify the stem elongation of a plant The network architecture was three layers network, input layer, hidden layer and output layer. The input data were environmental conditions, DIF and...
详细信息
A neural network was used to identify the stem elongation of a plant The network architecture was three layers network, input layer, hidden layer and output layer. The input data were environmental conditions, DIF and photoperiod, for plant growth, and the output data were coefficients of certain equation that represents plant stem elongation. The network was trained using the backpropagation algorithm. An experiment for measuring the stem elongation of a plant was conducted to collect data for verifying the network output.
In this paper, we present a new technique for mapping the backpropagation algorithm on hypercubes and related architectures. A key component of this technique is a network partitioning scheme called checkerboarding, C...
详细信息
In this paper, we present a new technique for mapping the backpropagation algorithm on hypercubes and related architectures. A key component of this technique is a network partitioning scheme called checkerboarding, Checkerboarding allows ns to replace the ail-to-all broadcast operation performed by the commonly used vertical network partitioning scheme, with operations that are much faster on the hypercubes and related architectures. Checkerboarding can be combined with the pattern partitioning technique to form a hybrid scheme that performs better than either one of these schemes. Theoretical analysis and experimental results on nCUBE(R) and CM5(R) show that our scheme performs better than the other schemes, for both uniform and nonuniform networks.
The paper examines the suitability of the generalized data rule in training artificial neural networks (ANN) for damage identification in structures. Several multilayer perceptron architectures are investigated for a ...
详细信息
The paper examines the suitability of the generalized data rule in training artificial neural networks (ANN) for damage identification in structures. Several multilayer perceptron architectures are investigated for a typical bridge truss structure with simulated damage stares generated randomly. The training samples have been generated in terms of measurable structural parameters (displacements and strains) at suitable selected locations in the structure. Issues related to the performance of the network with reference to hidden layers and hidden. neurons are examined. Some heuristics are proposed for the design of neural networks for damage identification in structures. These are further supported by an investigation conducted on five other bridge truss configurations.
This paper presents a multi-ANN approximation approach to approximate complex non-linear function. Comparing with single-ANN methods the proposed approach improves and increases the approximation and generalization ab...
详细信息
This paper presents a multi-ANN approximation approach to approximate complex non-linear function. Comparing with single-ANN methods the proposed approach improves and increases the approximation and generalization ability, and adaptability greatly in learning processes of networks. The simulation results have been shown that the method can be applied to the modeling and identification of complex dynamic control systems.
Artificial neural networks (ANN) based on the back-propagation algorithm (BP algorithm) were applied to a quantitative structure-activity relationship (QSAR) study for 30 azoxy compounds with antifungal activity. The ...
详细信息
Artificial neural networks (ANN) based on the back-propagation algorithm (BP algorithm) were applied to a quantitative structure-activity relationship (QSAR) study for 30 azoxy compounds with antifungal activity. The ANN model could well explain the variance of the antifungal activity owing to its ability to deal with a nonlinear tendency in the data set. A modified BP algorithm proposed by the authors has provided the ANN model with a more enhanced predictive capability. Finally a transformation of the final ANN model to a polynomial of original physico-chemical parameters was shown to be useful to elucidate the structural requirements for the antifungal activity.
OBJECTIVE: Our purpose was to evaluate an artificial neural network in the interpretation of nonstress tests, STUDY DESIGN: A nonlinear artificial neural network trained by backpropagation was taught to interpret reco...
详细信息
OBJECTIVE: Our purpose was to evaluate an artificial neural network in the interpretation of nonstress tests, STUDY DESIGN: A nonlinear artificial neural network trained by backpropagation was taught to interpret records of nonstress tests by two learning sets. The first set contained nonstress tests that were similarly interpreted by three human experts;the second set contained a subset of nonstress tests that led to interobserver disagreement. Both ''raw'' fetal heart rats and uterine contraction data and 17 quantified variables obtained by automated computer analysis were introduced to the input layer. After training, the network was tested by presenting it with input patterns to which it had not been exposed. The performance of the system was examined in relation to the human expert. RESULTS: After training the neural network with the first set, a sensitivity of 88.9% and a false-positive rate of 4.3% were obtained at testing. When the teaming acid test set contained records that led to interobserver disagreement, a sensitivity of 86.7% and a false-positive rate of 19.7% were obtained. Sixty percent of fetal heart rate records interpreted as abnormal by the neural network were interpreted likewise by the human experts. CONCLUSIONS: The results obtained are encouraging in that the neural network could discriminate between normal and abnormal nonstress tests. Further evaluation of this new technique is mandatory to evaluate its efficacy acid reliability in interpreting fetal heart rate records.
Fuzzy reasoning methods are generally classified into two approaches: the direct approach and the truth space approach. Several researches on the relationships between these approaches have been reported. There has be...
详细信息
Fuzzy reasoning methods are generally classified into two approaches: the direct approach and the truth space approach. Several researches on the relationships between these approaches have been reported. There has been, however;no research which discusses their utility. The authors have previously proposed four types of fuzzy neural networks (FNNs) called Type I, II, III, and IV. The FNNs can identify the fuzzy rules and tune the membership functions of fuzzy reasoning automatically, utilizing the learning capability of neural networks. Types III and IV;which ara based on the truth space approach, can acquire linguistic fuzzy rules with the fuzzy variables in the consequences labeled according to their linguistic truth values (LTVs). However, the expressions available for the linguistic labeling are limited since the LTVs are singletons. This paper presents a new type of FNN based on the truth space approach for automatic acquisition of the fuzzy rules with linguistic hedges. The new FNN, called Type V has the LTVs defined by fuzzy sets for fuzzy rules and can express the identified fuzzy rules linguistically using the fuzzy variables in the consequences with linguistic hedges. Two simulations are done for demonstrating the feasibility of the new method. The results show that the truth space approach makes the fuzzy rules easy to understand.
暂无评论