A mathematical discussion concerning the performance of multilayer perceptron-type artificial neural networks through use of orthogonal bipolar vectors

DOI10.1007/S40314-016-0377-XzbMath1391.68097OpenAlexW2515170201MaRDI QIDQ725715

Keiji Yamanaka, Shigueo Nomura, Edmilson Rodrigues Pinto, Tiago Elias Carvalho Oliveira, Igor Santos Peretta, José Ricardo Gonçalves Manzan

Publication date: 2 August 2018

Published in: Computational and Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s40314-016-0377-x

zbMATH Keywords

pattern recognitionmultilayer perceptronartificial neural networkEuclidean distanceAuslan signsconventional bipolar vectorhandwritten digitsiris humanorthogonal bipolar vectortarget vector

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Uses Software

• R
• UCI-ml
• CASIA Iris

Cites Work

• Unnamed Item
• Unnamed Item
• Trends in extreme learning machines: a review
• Expected energy-based restricted Boltzmann machine for classification
• Achieving a more robust neural network model for control of a MR damper by signal sensitivity analysis
• Improving prediction performance of neural networks in pattern classification
• A hybrid of electromagnetism-like mechanism and back-propagation algorithms for recurrent neural fuzzy systems design

This page was built for publication: A mathematical discussion concerning the performance of multilayer perceptron-type artificial neural networks through use of orthogonal bipolar vectors