Temporally Asymmetric Learning Supports Sequence Processing in Multi-Winner Self-Organizing Maps

DOI10.1162/089976604772744901zbMath1097.68117DBLPjournals/neco/SchulzR04OpenAlexW2134061151WikidataQ52001904 ScholiaQ52001904MaRDI QIDQ4823753

Reiner Schulz, James A. Reggia

Publication date: 28 October 2004

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/089976604772744901

zbMATH Keywords

sequence pattern recognition systems

Mathematics Subject Classification ID

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

Related Items (3)

A Model for Learning Topographically Organized Parts-Based Representations of Objects in Visual Cortex: Topographic Nonnegative Matrix Factorization ⋮ Mirror Symmetric Topographic Maps Can Arise from Activity-Dependent Synaptic Changes ⋮ Dynamics and Topographic Organization of Recursive Self-Organizing Maps

Cites Work

• Self-organized formation of topologically correct feature maps
• WEBSOM -- Self-organizing maps of document collections
• Why spikes? Hebbian learning and retrieval of time-resolved excitation patterns
• Speech dimensionality analysis on hypercubical self-organizing maps
• Computational consequences of temporally asymmetric learning rules. I: Differential Hebbian learning
• A Taxonomy for Spatiotemporal Connectionist Networks Revisited: The Unsupervised Case
• The Time-Organized Map Algorithm: Extending the Self-Organizing Map to Spatiotemporal Signals

This page was built for publication: Temporally Asymmetric Learning Supports Sequence Processing in Multi-Winner Self-Organizing Maps