Statistical methods in learning

Sutherland, A.; Henery, Bob; Molina, Rafael; Taylor, Charles; King, Ross D.

doi:10.1007/3-540-56735-6_54

Cited by 1 publication

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The particular implementation of the neural net strategy that was employed is Cascor, developed by Fahlman and Lebiere (1990) and used in a similar large-scale simulation comparison of classification methods, described in Sutherland et al (1993). It was chosen because it learns more rapidly than standard feedforward nets with backpropagation training, because it was used previously in a major comparison, and because it adaptively chooses the number of hidden nodes, thereby making the analysis more automatic.…”

Section: Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Comparing Methods for Multivariate Nonparametric Regression

Banks

Olszewski

Maxion

2003

Communications in Statistics - Simulation and Computation

View full text Add to dashboard Cite

The ever-growing number of high-dimensional, superlarge databases requires effective analysis techniques to mine interesting information from the data. Development of new-wave methodologies for high-dimensional nonparametric regression has exploded over the last decade in an effort to meet these analysis demands. This paper reports on an extensive simulation experiment that compares the performance of ten different, commonly-used regression techniques: linear regression, stepwise linear regression, additive models (AM), projection pursuit regression (PPR), recursive partitioning regression (RPR), multivariate adaptive regression splines (MARS), alternating conditional expectations (ACE), additivity and variance stabilization (AVAS), locally weighted regression (LOESS), and neural networks. Each regression technique was used to analyze multiple datasets each having a unique embedded structure; the accuracy of each technique was determined by its ability to correctly identify the embedded structure averaged over all the datasets. Datasets used in the experiment were constructed to have a range of characteristics by varying the dimension of the data, the true dimension of the embedded structure, the sample size, the amount of noise, and the complexity of the embedded structure. Analyses of the results show that all of these properties affect the accuracy of each regression technique under investigation. A mapping from data characteristics to the most effective regression technique(s) is suggested.

show abstract

Section: Neural Networkmentioning

confidence: 99%

“…By contrast, classification is better understood; see Ripley (1994aRipley ( , 1994bRipley ( , 1996 and Sutherland et al (1993) for comparative evaluations of neural networks against more traditional statistical methodologies.…”

Section: Introductionmentioning

confidence: 99%