Optimal ensemble averaging of neural networks

Naftaly, Ury; Intrator, Nathan; Horn, D.

doi:10.1088/0954-898x/8/3/004

Cited by 69 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A more targeted approach to aggregation might yield superior results, and a different aggregation approach might be best served with a different training methodology. For example, over-trained networks have been shown to perform better in large ensembles than under-trained networks (Naftaly et al, 1997;Granitto et al, 2005).…”

Section: Discussionmentioning

confidence: 99%

Using multi-pyranometer arrays and neural networks to estimate direct normal irradiance

et al. 2015

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Using multi-pyranometer arrays and neural networks to estimate direct normal irradiance

et al. 2015

View full text Add to dashboard Cite

“…The proposed model is trained by using three different ANN networks such as cascade-forward back propagation network (NEWCF), feed-forward input time-delay back propagation network (NEWFFTD), and fitting network (NEWFIT) ,each network is trained by using ensemble methods under different combination of groups by applying two methods which are the averaging and voting methods [8].…”

Section: Methodsmentioning

confidence: 99%

Performance of Cancer Prediction Based on Artificial Neural Network

2014

Universal Researchers (UR) Dec. 25-26, 2014 at Dubai (UAE)

View full text Add to dashboard Cite

“…So we should not expect a reduction in the bias term compared to single models. According to Naftaly et al [27], the variance term of the ensemble could be decomposed in the following way:…”

Section: Theory and Methodsmentioning

confidence: 99%

Classification Models for Detection of Lung Cancer Based on Nine Element Distribution of Urine Samples

Tan

Chen

2010

Biol Trace Elem Res

View full text Add to dashboard Cite

The detection of lung cancer has a special value in the diagnosis of cancer diseases. Based on nine elemental concentrations (i.e., chromium, iron, manganese, aluminum, cadmium, copper, zinc, nickel, and selenium) in urine samples and an ensemble linear discriminant analysis (ELDA), a detection method for lung cancer has been developed. A dataset containing 30 healthy samples and 27 lung cancer samples is used for experiment. The whole dataset was first split into a training set with 29 samples and a test set with 28 samples. The prediction results from the ELDA classifier were compared with those from single Fisher's discriminate analysis (FDA). On the test set, the ELDA classifier achieved better performance, that is, a sensitivity of 100%, a specificity of 86.7%, and an overall accuracy of 92.9%, while the FDA classifier had a sensitivity of 92.3%, a specificity of 93.3%, and an overall accuracy of 92.9%. The superiority of ELDA to FDA is ascribed to the fact that ELDA can model more nonlinear relationships through the cooperation of several single models, suggesting that ensemble modeling is more advisable in such a task.

show abstract

Optimal ensemble averaging of neural networks

Cited by 69 publications

References 8 publications

Using multi-pyranometer arrays and neural networks to estimate direct normal irradiance

Using multi-pyranometer arrays and neural networks to estimate direct normal irradiance

Performance of Cancer Prediction Based on Artificial Neural Network

Classification Models for Detection of Lung Cancer Based on Nine Element Distribution of Urine Samples

Contact Info

Product

Resources

About