Publication | Closed Access
Neural networks for exact matching of functions on a discrete domain
16
Citations
5
References
1990
Year
Unknown Venue
Artificial IntelligenceEngineeringMachine LearningNeural Networks (Machine Learning)Graph MatchingSocial SciencesDiscrete DomainPattern RecognitionSparse Neural NetworkN Distinct PointsPattern AnalysisApproximation TheoryComputational Learning TheoryComputer EngineeringComputer ScienceNeural Networks (Computational Neuroscience)Neural NetworksStatistical Pattern RecognitionDeep LearningNeural Architecture SearchDeep Neural NetworksExact MatchingCellular Neural NetworkPattern Recognition Application
In many pattern classification problems it is desirable to realize functions defined on a discrete domain. The authors consider the exact matching of such functions through a three-layered perceptron-based neural network. It is shown that, for a function defined at N distinct points, exact matching can be accomplished through a network with N-1 hidden layer nodes. A construction procedure involving a matrix inversion is also presented.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
| Year | Citations | |
|---|---|---|
Page 1
Page 1