Cargando…
Reinforcement Learning on Slow Features of High-Dimensional Input Streams
Humans and animals are able to learn complex behaviors based on a massive stream of sensory information from different modalities. Early animal studies have identified learning mechanisms that are based on reward and punishment such that animals tend to avoid actions that lead to punishment whereas...
Autores principales: | Legenstein, Robert, Wilbert, Niko, Wiskott, Laurenz |
---|---|
Formato: | Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2010
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2924248/ https://www.ncbi.nlm.nih.gov/pubmed/20808883 http://dx.doi.org/10.1371/journal.pcbi.1000894 |
Ejemplares similares
-
Slow Feature Analysis on Retinal Waves Leads to V1 Complex Cells
por: Dähne, Sven, et al.
Publicado: (2014) -
Modeling place field activity with hierarchical slow feature analysis
por: Schönfeld, Fabian, et al.
Publicado: (2015) -
Context-dependent extinction learning emerging from raw sensory inputs: a reinforcement learning approach
por: Walther, Thomas, et al.
Publicado: (2021) -
Spike-timing-dependent plasticity and temporal input statistics
por: Sprekeler, Henning, et al.
Publicado: (2007) -
Modular Toolkit for Data Processing (MDP): A Python Data Processing Framework
por: Zito, Tiziano, et al.
Publicado: (2009)