On hidden nodes for neural nets

Mirchandani, G.; Cao, Wei

doi:10.1109/31.31313

Cited by 261 publications

(88 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…samples of each class which are near to or bordering on those samples in different classes, are better than randomly selected samples for training ANNs constructed for classification purposes [13]. The distributions of survivors and nonsurvivors across the APACHE II score range are shown in Fig.…”

Section: Data Preparationmentioning

confidence: 99%

A comparison of ICU mortality prediction using the APACHE II scoring system and artificial neural networks

Wong¹,

Young

1999

Anaesthesia

View full text Add to dashboard Cite

SummaryThe aim of this study was to compare the ability of artificial neural networks and the Acute Physiology and Chronic Health Evaluation II score to predict mortality in adult intensive care units. The same physiological variables were used in both predictive models to predict hospital mortality from a data set of 8796 patients collected from 26 adult intensive care units in the United Kingdom and Ireland as part of the Intensive Care Society study. The results from the two models were compared with the actual outcome. The overall prediction accuracy and the overall goodness-of-fit of all the models were assessed. Both predictive models showed similar goodnessof-fit and prediction discrimination. The overall predictive and classification performance of the artificial neural network developed matched and in some aspects was better than that of Acute Physiology and Chronic Health Evaluation II.

show abstract

Section: Data Preparationmentioning

confidence: 99%

A comparison of ICU mortality prediction using the APACHE II scoring system and artificial neural networks

Wong¹,

Young

1999

Anaesthesia

View full text Add to dashboard Cite

show abstract

“…Output layer 1 proposed by Lippmann (1987), Mirchandani and Cao (1989) and Maren et al (1988), it is found that a network with two hidden layers, 20 nodes in the first hidden layer and 4 nodes in the second hidden layer, can converge reasonably fast and provide sufficient calculation accuracy. Figure 6 shows the architectures of MOBP neural network for interpreting low-resistivity pay zone.…”

Section: Input Layermentioning

confidence: 99%

Application of momentum backpropagation algorithm (MOBP) in identification of low-resistivity pay zones in sandstones

Bao

Yuan

et al. 2016

J Petrol Explor Prod Technol

View full text Add to dashboard Cite

Low-resistivity pay zones with substantial reserves in many oilfields around the world are drawing more attention than ever before. Through analyzing the features of the logging data in low-resistivity pay zones, a fast model for identification of low-resistivity pay zones was developed in this paper. Momentum backpropagation algorithm was used in the model development. Indicators that can amplify the characteristics of low-resistivity pay zones were designed. The proposed model can be used for reevaluating old wells using conventional logging data. Validations through field examples demonstrated the capability of the model in accurate identification of lowresistivity pay zones.

show abstract

“…Research has proposed various methods for selection of hidden nodes in the hidden layer (see Chang-Xue, ZhiGuang and Kusiak, 2005), as follows: Marchandani and Cao, 1989)  H 5 = O(I + 1) (Lipmann, 1987) Here, I is the number of inputs, O is the number of output neurons, and n is the number of training data points.…”

Section: Selection Of Hidden Layer and Hidden Nodesmentioning

confidence: 99%

Variable Selection in Regression using Multilayer Feedforward Network

Kamble

Kashid

2016

J. Mod. App. Stat. Meth.

View full text Add to dashboard Cite

The selection of relevant variables in the model is one of the important problems in regression analysis. Recently, a few methods were developed based on a model free approach. A multilayer feedforward neural network model was proposed for developing variable selection in regression. A simulation study and real data were used for evaluating the performance of proposed method in the presence of outliers, and multicollinearity.

show abstract

On hidden nodes for neural nets

Cited by 261 publications

References 2 publications

A comparison of ICU mortality prediction using the APACHE II scoring system and artificial neural networks

A comparison of ICU mortality prediction using the APACHE II scoring system and artificial neural networks

Application of momentum backpropagation algorithm (MOBP) in identification of low-resistivity pay zones in sandstones

Variable Selection in Regression using Multilayer Feedforward Network

Contact Info

Product

Resources

About