Confidence in prediction by neural networks

Liat Ein-Dor, Ido Kanter

Research output: Contribution to journalArticlepeer-review

12 Scopus citations


The idea that a trained network can assign a confidence number to its prediction, indicating the level of its reliability, is addressed and exemplified by an analytical examination of a perceptron with discrete and continuous output units. Results are derived for both Gibbs and Bayes scenarios. The information gain by the confidence number is estimated by various entropy measurements.

Original languageEnglish
Pages (from-to)799-802
Number of pages4
JournalPhysical Review E
Issue number1
StatePublished - Jul 1999


Dive into the research topics of 'Confidence in prediction by neural networks'. Together they form a unique fingerprint.

Cite this