Network information criterion-determining the number of hidden units for an artificial neural network model

Authors:
N. Murata;S. Yoshizawa;S. Amari
Affiliations:
Dept. of Math. Eng. & Inf. Phys., Tokyo Univ.;-;-
Venue:
IEEE Transactions on Neural Networks
Year:
1994

Citing 0
Cited 22

Stochastic complexities of reduced rank regression in Bayesian estimation

Neural Networks
The implementation of neural network for semiconductor PECVD process

Expert Systems with Applications: An International Journal
A neural-network approach for an automatic LED inspection system

Expert Systems with Applications: An International Journal
2007 Special Issue: Fast neural network surrogates for very high dimensional physics-based models in computational oceanography

Neural Networks
Learning algorithm of wavelet network based on sampling theory

Neurocomputing
A three-stage integrated approach for assembly sequence planning using neural networks

Expert Systems with Applications: An International Journal
Relation between weight size and degree of over-fitting in neural network regression

Neural Networks
A neural network-based approach for dynamic quality prediction in a plastic injection molding process

Expert Systems with Applications: An International Journal
Letters: Prediction error of a fault tolerant neural network

Neurocomputing
Model optimizing and feature selecting for support vector regression in time series forecasting

Neurocomputing
Process parameter optimization for MIMO plastic injection molding via soft computing

Expert Systems with Applications: An International Journal
Design of experiments on neural network's training for nonlinear time series forecasting

Neurocomputing
A systematic optimization approach for assembly sequence planning using Taguchi method, DOE, and BPNN

Expert Systems with Applications: An International Journal
Artificial neural network for the joint modelling of discrete cause-specific hazards

Artificial Intelligence in Medicine
Improving weighted information criterion by using optimization

Journal of Computational and Applied Mathematics
A new architecture selection method based on tabu search for artificial neural networks

Expert Systems with Applications: An International Journal
CAST: Using neural networks to improve trading systems based on technical analysis by means of the RSI financial indicator

Expert Systems with Applications: An International Journal
Learning in a higher-order simple perceptron

Mathematical and Computer Modelling: An International Journal
Linear support vector machines via dual cached loops

Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining
Evolutionary artificial neural networks: a review

Artificial Intelligence Review
A Study on the Contribution of 12 Key-Factors to the Growth Rates of the Region of the East Macedonia-Thrace EMTH by Using a Neural Network Model

International Journal of Productivity Management and Assessment Technologies
On-line prediction of the feeding phase in high-cell density cultivation of rE. coli using constructive neural networks

Computer Methods and Programs in Biomedicine

Quantified Score

Hi-index	0.02

Visualization

Abstract

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 (i.e., unrealizable) models with general loss criteria including regularization terms. The relation between the training error and the generalization error is studied in terms of the number of the training examples and the complexity of a network which reduces to the number of parameters in the ordinary statistical theory of AIC. This relation leads to a new network information criterion which is useful for selecting the optimal network model based on a given training set