Parallel processing of chemical information in a local area network—II. A parallel cross-validation procedure for artificial neural networks

Derks, E.P.P.A.; Beckers, M.L.M.; Melssen, W.J.; Buydens, L.M.C.

doi:10.1016/0097-8485(95)00085-2

Cited by 30 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data were preprocessed as in the PCA analysis. As we did not have many measurements cross validation was applied to check the performance of the network [18]. The training set was six measurements for each type of wine and three for each type of alcohol concentration.…”

Section: Statistical Proceduresmentioning

confidence: 99%

A comparative study of sensor array and GC–MS: application to Madrid wines characterization

Santos

Arroyo

Aleixandre

et al. 2004

Sensors and Actuators B: Chemical

View full text Add to dashboard Cite

Section: Statistical Proceduresmentioning

confidence: 99%

A comparative study of sensor array and GC–MS: application to Madrid wines characterization

Santos

Arroyo

Aleixandre

et al. 2004

Sensors and Actuators B: Chemical

View full text Add to dashboard Cite

“…One group has demonstrated a method of parallel processing the cross validation studies across a local area network [44] which may address this problem.…”

Section: Ann Models and Problemsmentioning

confidence: 99%

Applications of soft computing in drug design

Maddalena¹

1998

Expert Opinion on Therapeutic Patents

View full text Add to dashboard Cite

This review examines the role of soft computing methods such as artificial neural networks (ANNs), genetic algorithms (GAs), fuzzy logic (FL), chaos, fractals and cellular automata (CA) and their hybrids in the field of drug design. They have been found to be useful in a wide variety of areas including quantitative structure-activity relationship (QSAR), quantitative structure-property relationship (QSPR), variable selection, conformation searching, receptor docking, pharmacophore development, molecular design, combinatorial libraries, surface phenomena, kinetics and complex system studies. Based upon the studies examined, the use of soft computing techniques is likely to grow significantly in the future.

show abstract

“…A probabilistic neural network (PNN) was used for classification purposes. The PNN was composed by three layers: the input one had three neurons, corresponding to the three principal components; the hidden layer (with radial basis transfer functions) had the same number of neurons as the number of training vectors and a competitive layer in the output (Duda et al, 2001), leave one out (LOO) cross validation method applied to the network in order to check the performance of the network (Derks et al, 1995). LOO consists of training N distinct nets (in this case, N is number of measurements) by using NÀ1 training vectors, while the validation of the trained net is carried out by using the remaining vector, excluded from the training set.…”

Section: Data Processingmentioning

confidence: 99%