Fundamentals of Artificial Neural Networks

Hassoun, M.H.

doi:10.1109/jproc.1996.503146

Cited by 696 publications

(273 citation statements)

References 7 publications

Supporting

Mentioning

260

Contrasting

Unclassified

Order By: Relevance

“…In this section we shall test the generalization capability of the proposed method and perform comparative evaluations against the most promising, state-of-the-art evolutionary techniques, over a benchmark dataset, which is partitioned into three sets: training, validation and testing. There are several techniques (Hassoun, 1995) to use training and validation sets individually to prevent over-fitting and thus to improve the classification performance in the test data. However, the use of validation set should not be needed for EA based techniques since they search globally for a solution (Sexton & Dorsey, 2000).…”

Section: Medical Diagnosis Problems From Proben1mentioning

confidence: 99%

Evolutionary artificial neural networks by multi-dimensional particle swarm optimization

et al. 2009

View full text Add to dashboard Cite

Section: Medical Diagnosis Problems From Proben1mentioning

confidence: 99%

Evolutionary artificial neural networks by multi-dimensional particle swarm optimization

et al. 2009

View full text Add to dashboard Cite

“…According to Kolmogorov Theory [2] , a BPNN with single hidden layer can realize an non-linear mapping from n-dimension to m-dimension, in the other words, any continuous function in a closed interval can be infinitely approximated using a BPNN with single hidden layer. Therefore, only one hidden layer is designed in the NN for configuration price prediction in this paper.…”

Section: Nn Prediction Model With Adjustable Number Of Hidden Layer Nmentioning

confidence: 99%

“…In view of the high degree of self-learning ability of neural network and approximating nonlinear function with arbitrary precision, it is suitable for simulation of complex nonlinear system [2] . In order to solve the aforementioned configuration price prediction problem, a new prediction method is proposed based on neural network with adjustable number of hidden layer nodes.…”

Section: Introductionmentioning

confidence: 99%

Product Family Configuration Price Prediction Based On Neural Network

Lai¹,

Lin²,

Wu³

2018

dtcse

View full text Add to dashboard Cite

Abstract. In order to quickly and effectively respond to customer enquiry in the dynamic changeable market, a new method for product family configuration price prediction is proposed based on neural network with adjustable number of hidden layer nodes. Based on product family configuration history of various product variants and the corresponding prices, the relationship model between the product configuration and price is established using neural network, which is utilized to predict the market price of the newly configured product variant for some random order.

show abstract

“…The guidance process is an implicit process that evaluates the relative quality of search points and biases the exploration process to move toward regions of high-quality solutions in W. The convergence-inducing process finally ensures the convergence of the search to find a fixed solutionŵ . The dynamic interaction among these three processes is responsible for giving the search process its global optimizing character (Hassoun, 1995). An example of a powerful global search procedure is Alopex, a correlationbased method for solving the maximum likelihood problem.…”

Section: Parameter Estimation and Proceduresmentioning

confidence: 99%

Principles of Neural Spatial Interaction Modeling

Fischer

2009

Advances in Spatial Science

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in EconStor may Principles of Neural SpatialInteraction Modelling MANFRED M. FISCHER Department of Economic Geography & Geoinformatics Vienna University of Economics and Business Administration AbstractNeural spatial interaction models represent the most recent innovation in the design of spatial interaction models. They are receiving increasing attention in recent years because of their powerful universal approximation properties. In essence they are devices for non-parametric statistical inferences, providing an elegant formalism for spatial interaction modelling. This contribution meets an urgent demand for methodological guidelines on how to develop robust applications that work from a statistical perspective. It introduces various components of a methodology for neural spatial interaction modelling that consists of a model specification framework to produce consistent estimators, a parameter estimation framework to compute parameter estimates that optimize an explicit fitness criterion and a framework to evaluate the model performance.JEL classification: C31, C45, R19

show abstract

Fundamentals of Artificial Neural Networks

Cited by 696 publications

References 7 publications

Evolutionary artificial neural networks by multi-dimensional particle swarm optimization

Evolutionary artificial neural networks by multi-dimensional particle swarm optimization

Product Family Configuration Price Prediction Based On Neural Network

Principles of Neural Spatial Interaction Modeling

Contact Info

Product

Resources

About