Boosting neural network feature extraction by reduced accuracy activation functions

DOI10.1016/S0031-3203(02)00166-8zbMath1028.68126OpenAlexW2079990344MaRDI QIDQ1402707

A. Raudys

Publication date: 28 August 2003

Published in: Pattern Recognition (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0031-3203(02)00166-8

zbMATH Keywords

Multilayer perceptronFeature extractionActivation functionAuto associative neural networkLimited precisionLookup table

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• An overview of mapping techniques for exploratory pattern analysis
• Auto-association by multilayer perceptrons and singular value decomposition
• Improving backpropagation learning under limited precision
• A comparative study of neural network based feature extraction paradigms
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Boosting neural network feature extraction by reduced accuracy activation functions