Review on Methods to Fix Number of Hidden Neurons in Neural Networks
K. Gnana Sheela,S. N. Deepa +1 more
TLDR
The experimental results show that with minimum errors the proposed approach can be used for wind speed prediction in renewable energy systems and the perfect design of the neural network based on the selection criteria is substantiated using convergence theorem.Citations
More filters
Journal ArticleDOI
Practical options for selecting data-driven or physics-based prognostics algorithms with reviews
TL;DR: It is concluded that the Gaussian process is easy and fast to implement, but works well only when the covariance function is properly defined, and the neural network has the advantage in the case of large noise and complex models but only with many training data sets.
Journal ArticleDOI
A SEM-neural network approach for predicting antecedents of m-commerce acceptance
TL;DR: The results showed that customization and customer involvement are the strongest antecedents of the intention to use m-commerce, which will be useful for m- commerce providers in formulating optimal marketing strategies to attract new consumers.
Journal ArticleDOI
Predicting the determinants of mobile payment acceptance: A hybrid SEM-neural network approach
TL;DR: A new research model used for the prediction of the most significant factors influencing the decision to use m-payment found that the mostificant variables impacting the intention to use were perceived usefulness and perceived security variables.
Journal ArticleDOI
Daily wind speed forecasting through hybrid KF-ANN model based on ARIMA
TL;DR: In this article, an artificial neural network (ANN) and Kalman filter (KF) were used to handle nonlinearity and uncertainty problems in wind speed forecasting in order to improve the accuracy of wind power generation.
Journal ArticleDOI
A survey on the application of recurrent neural networks to statistical language modeling
TL;DR: This paper presents a survey on the application of recurrent neural networks to the task of statistical language modeling, and gives an overview of the most important extensions.
References
More filters
Book
An introduction to neural networks
TL;DR: An Introduction to Nueral Networks will be warmly welcomed by a wide readership seeking an authoritative treatment of this key subject without an intimidating level of mathematics in the presentation.
Journal ArticleDOI
Learning capability and storage capacity of two-hidden-layer feedforward networks
TL;DR: This paper rigorously proves in a constructive method that two-hidden-layer feedforward networks (TLFNs) with 2/spl radic/(m+2)N (/spl Lt/N) hidden neurons can learn any N distinct samples with any arbitrarily small error, where m is the required number of output neurons.
Journal ArticleDOI
Network information criterion-determining the number of hidden units for an artificial neural network model
TL;DR: The problem of model selection, or determination of the number of hidden units, can be approached statistically, by generalizing Akaike's information criterion (AIC) to be applicable to unfaithful models with general loss criteria including regularization terms.
Journal ArticleDOI
Capabilities of a four-layered feedforward neural network: four layers versus three
S. Tamura,M. Tateishi +1 more
TL;DR: A proof is given showing that a three-layered feedforward network with N-1 hidden units can give any N input-target relations exactly, and a four-layering network is constructed and is found to give anyN input- target relations with a negligibly small error using only (N/2)+3 hidden units.