✦ LIBER ✦

Model selection in neural networks

✍ Scribed by Ulrich Anders; Olaf Korn

Publisher: Elsevier Science
Year: 1999
Tongue: English
Weight: 418 KB
Volume: 12
Category: Article
ISSN: 0893-6080
DOI: 10.1016/s0893-6080(98)00117-8

No coin nor oath required. For personal study only.

✦ Synopsis

In this article, we examine how model selection in neural networks can be guided by statistical procedures such as hypothesis tests, information criteria and cross validation. The application of these methods in neural network models is discussed, paying attention especially to the identification problems encountered. We then propose five specification strategies based on different statistical procedures and compare them in a simulation study. As the results of the study are promising, it is suggested that a statistical analysis should become an integral part of neural network modeling.

📜 SIMILAR VOLUMES

Neural network models in a set selection

Neural network models in a set selection problem

✍ Youry R. Romanovsky; Egor D. Brovko 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 151 KB

WE INTRODUCE A CONTINUOUS FAMILY OF HIGH ORDER NEURAL NETWORK MODELS WHICH SOLVE THE SET SELECTION PROBLEM: given a finite list of finite sets, find a set that intersects each of them in exactly one element. The additive model proposed earlier by Clark Jeffries belongs to this family. We study defor

Variation and selection: An evolutionary

Variation and selection: An evolutionary model of learning in neural networks

✍ Aviv Bergman 📂 Article 📅 1988 🏛 Elsevier Science 🌐 English ⚖ 53 KB

The diversity of the living world has been shaped, it is believed, by Darwinian selection acting on random mutations. This paper deal with the same problem that evolution had to solve --how to form categories in a bottom-up manner from information in the environment, without incorporating the assump

Unbiased estimate of generalization erro

Unbiased estimate of generalization error and model selection in neural network

✍ Yong Liu 📂 Article 📅 1995 🏛 Elsevier Science 🌐 English ⚖ 410 KB

Selection of the most significant parame

Selection of the most significant parameters for duration modelling in a Spanish text-to-speech system using neural networks

✍ Ricardo Córdoba; Juan M. Montero; Juana M. Gutiérrez; José A. Vallejo; Emilia En 📂 Article 📅 2002 🏛 Elsevier Science 🌐 English ⚖ 163 KB

Accurate prediction of segmental duration from text in a text-to-speech system is difficult for several reasons. One which is especially relevant is the great quantity of contextual factors that affect timing and it is difficult to find the right way to model them. There are many parameters that aff

Toward an Optimal Approach for Variable

Toward an Optimal Approach for Variable Selection in Counter-Propagation Neural Networks: Modeling Protein-Tyrosine Kinase Inhibitory of Flavanoids Using Substituent Electronic Descriptors

✍ Bahram Hemmateenejad ; Ahmadreza Mehdipour; Omar Deeb; Mahmood Sanchooli; Ramin 📂 Article 📅 2011 🏛 Wiley (John Wiley & Sons) 🌐 English ⚖ 431 KB

## Abstract Counter propagation neural network (CPNN) is one of the attractive tools of classification in QSAR studies. A major obstacle in classification by CPNN is finding the best subset of variables. In this study, the performance of some different feature selection algorithms including F score

SELECTION OF TRAINING SAMPLES FOR MODEL

SELECTION OF TRAINING SAMPLES FOR MODEL UPDATING USING NEURAL NETWORKS

✍ C.C. CHANG; T.Y.P. CHANG; Y.G. XU; W.M. TO 📂 Article 📅 2002 🏛 Elsevier Science 🌐 English ⚖ 362 KB

One unique feature of neural networks is that they have to be trained to function. In developing an iterative neural network technique for model updating of structures, it has been shown that the number of training samples required increases exponentially as the number of parameters to be updated in