Modeling with Neural Networks: Principles and Model Design Methodology

Dreyfus, Gérard

doi:10.1007/3-540-28847-3_2

Cited by 94 publications

(154 citation statements)

References 34 publications

Supporting

Mentioning

152

Contrasting

Unclassified

Order By: Relevance

“…The similarity between ANN techniques and traditional methods in statistics and econometrics has been investigated in the literature (Cheng & Titterington, 1994;Ripley, 1994;Hwang et al, 1994;Kuan & White, 1994;Dreyfus, 2005).…”

Section: Function Approximation With Artificial Neural Networkmentioning

confidence: 99%

Forecasting a Mix of Temporal and Non-Temporal Economic Variables with a Mixture-of-Experts Neural Network

Nguyen¹,

Kira²

2018

IJEF

View full text Add to dashboard Cite

This study investigates a versatile forecasting technique using an integrated system of Artificial Neural Networks (ANN) and Genetic Algorithms (GA) in a mixture-of-experts architecture to solve a general economic forecasting problem involving a mix of temporal and non-temporal variables. Using Klein Model I as a context and previous estimations from traditional methods as benchmarks, the study provides evidence on the effectiveness and efficiency of this integrated system. ANN helps overcome the imposition of assumptions on the behaviors of related variables, the specification of exact relationships, and the difficulty in nonlinear estimations of the economic model. GA helps overcome the sub-optimality of the tedious trial-and-error process in network building. The flexibility of the mixture-of experts network architecture offers many alternative configurations to capture the peculiarities of variables in context before aggregating intermediate estimations into the final result. The integrated system has shown its ability in processing effectively the mixture of economic variables, and producing efficient estimations and forecasts.

show abstract

Section: Function Approximation With Artificial Neural Networkmentioning

confidence: 99%

Forecasting a Mix of Temporal and Non-Temporal Economic Variables with a Mixture-of-Experts Neural Network

Nguyen¹,

Kira²

2018

IJEF

View full text Add to dashboard Cite

show abstract

“…In Schmitz and Cullmann (2008), the generalization step is assessed on an independent test set, but the most intense event of the database is always included in the training set. The importance of such issues was studied by Toukourou (2009), who employed cross-validation (Dreyfus et al, 2004) in order to select model complexity and variables.…”

Section: State-of-the-art Assessmentmentioning

confidence: 99%

“…The interested reader is referred to Dreyfus et al (2004) for the fundamentals on neural networks. Only the main properties are presented herein.…”

Section: Universal Approximationmentioning

confidence: 99%

“…Some are referred to as active (examples include early stopping), while other methods are called passive (these include cross-validation (Dreyfus et al, 2004)). Early stopping consists of observing generalization performance on an independent dataset (i.e.…”

Section: Accuracy and Generalizationmentioning

confidence: 99%

“…Training was then performed K times on K subsets (Dreyfus et al, 2004), with the mean squared error also being calculated K times on each validation set. The validation score could be calculated afterwards.…”

Section: Model Selection By Cross-validationmentioning

confidence: 99%

See 2 more Smart Citations

Complexity selection of a neural network model for karst flood forecasting: The case of the Lez Basin (southern France)

Siou

Johannet

Estupina

et al. 2011

Journal of Hydrology

View full text Add to dashboard Cite

A neural network model is applied to simulate the rainfall-runoff relation of a karst spring. The input selection for such a model becomes a major issue when deriving a parsimonious and efficient model. The present study is focused on these input selection methods; it begins by proposing two such methods and combines them in a subsequent step. The methods introduced are assessed for both simulation and forecasting purposes. Since rainfall is very difficult to forecast, especially in the study area, we have chosen a forecasting mode that does not require any rainfall forecast assumptions. This application has been implemented on the Lez karst aquifer, a highly complex basin due to its structure and operating conditions. Our models yield very good results, and the forecasted discharge values at the Lez spring are acceptable up to a 1-day forecasting horizon. The combined input selection method ultimately proves to be promising, by reducing input selection time while taking into account: i) the model's ability to accommodate nonlinearity, and ii) the forecasting horizon.

show abstract

Weight learning for ℋ∞$$ {\mathscr{H}}_{\infty } $$ stabilization of uncertain switched neural networks with external disturbance and reaction‐diffusion

Tai

Gao

Zhao

et al. 2023

Adaptive Control & Signal

View full text Add to dashboard Cite

This paper considers the  ∞ stabilization of uncertain switched neural networks with external disturbance and reaction-diffusion. A weight learning rule that ensures the  ∞ stability of the network is proposed utilizing the Lyapunov-Krasovskii functional method. Then, a useful lemma concerning the equivalence of matrix inequities is derived. With the aid of the lemma and Schur complement, a more concise existence condition on the learning rule is developed. Finally, theoretical comparisons and a numerical example are given, which show that the obtained results are extensions and improvements of an existing result.

show abstract

Modeling with Neural Networks: Principles and Model Design Methodology

Cited by 94 publications

References 34 publications

Forecasting a Mix of Temporal and Non-Temporal Economic Variables with a Mixture-of-Experts Neural Network

Forecasting a Mix of Temporal and Non-Temporal Economic Variables with a Mixture-of-Experts Neural Network

Complexity selection of a neural network model for karst flood forecasting: The case of the Lez Basin (southern France)

Weight learning for ℋ∞$$ {\mathscr{H}}_{\infty } $$ stabilization of uncertain switched neural networks with external disturbance and reaction‐diffusion

Contact Info

Product

Resources

About