Incremental class learning approach and its application to handwritten digit recognition

DOI10.1016/S0020-0255(02)00170-6MaRDI QIDQ1858415zbMATH OpenOpenAlexFDO

Authors Jacek Mańdziuk, Lokendra Shastri

Publication date 13 February 2003

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/s0020-0255(02)00170-6

zbMATH Keywords

supervised learningpattern recognitionneural networkhandwritten digit recognitioncatastrophic interference problemincremental class learningspatio-temporalrepresentation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Computing methodologies and applications (68U99)

Recommendations

• Adaptive object recognition model using incremental feature representation and hierarchical classification
• scientific article; zbMATH DE number 1927402
• scientific article; zbMATH DE number 2033158
• Neocognitron capable of incremental learning
• Progressive learning: a deep learning framework for continual learning

Cites work

• scientific article; zbMATH DE number 886124 (Why is no real title available?)
• A massively parallel architecture for a self-organizing neural pattern recognition machine
• Self-organized formation of topologically correct feature maps

Cited in

(5)

• scientific article; zbMATH DE number 1927402 (Why is no real title available?)
• Risk-sensitive loss functions for sparse multi-category classification problems
• Adaptive object recognition model using incremental feature representation and hierarchical classification
• Incremental tensor principal component analysis for handwritten digit recognition
• Achieving a compromise between performance and complexity of structure: an incremental approach

This page was built for publication: Incremental class learning approach and its application to handwritten digit recognition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1858415)