Self-organization of orientation sensitive cells in the striate cortex

Malsburg, Christoph von der

doi:10.1007/bf00288907

Cited by 1,313 publications

(377 citation statements)

References 18 publications

Supporting

Mentioning

359

Contrasting

Unclassified

Order By: Relevance

“…In a competitive learning network (Grossberg, 1972(Grossberg, , 1976bMalsburg, 1973) inputs I; filtered through adaptive pathways produce activations Yj at nodes of a target competitive field F 2 . At active F 2 nodes, instar learning (57) strengthens the net signal sent by the active input I.…”

Section: Distributed Competitive Learningmentioning

confidence: 99%

Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks

1997

View full text Add to dashboard Cite

Section: Distributed Competitive Learningmentioning

confidence: 99%

Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks

1997

View full text Add to dashboard Cite

“…Indeed, these authors also stated that "our analyses differ from many of these [former analyses] in that we focus on the development of feature detectors rather than pattern classification" (p. 76). A glance at such titles as Malsburg (1973) and Grossberg (1976aGrossberg ( , 1976b shows that this observation is also inaccurate.…”

Section: Feature Discovery By Competitive Learningmentioning

confidence: 99%

Competitive learning: From interactive activation to adaptive resonance

1987

View full text Add to dashboard Cite

Functional and mechanistic comparisons are made between several network models of cognitive processing: competitive learning, interactive activation, adaptive resonance, ond back propagation. The starting point of this comparison is the article of Rumelhart and Zipser (1985) on feature discovery through compotitive learning. All the models which Rumelhart and Zipser (1985) have described were shown in Grossberg (1976b) to exhibit a iype of learning which is temporally unstable. Competitive learning mechanisms con be stabilized in response to an arbitrary input environmmt by being supplemented with mechanisms for learning top-down expoctancies, or templates; for matching bottom-up input patternr with the top-down expectancies: and for releasing orienting reactions in a mismatch situation, thereby updating short-term memory and searching for another internal representation. Network architectures which embody all of these mochanisms were called adaptive resonance models by Grossberg (1976~). Self-stobilizing learning models are candidater for use in root-world applications where unpredictable changes can occur in complex input environments. Competitive learning postulates are inconsistent with the postulates of the interactive activation model of McClelland and Rumelhart (1981), and suggest different levels of processing and interaction rules for the analysis of word recognition. Adaptive resononce models use these alternative levels and interaction rules. The selforganizing learning of an adoptive resonance model is compared and contrasted with the teacher-directed learning of a back propogation model. A number of criteria for evaluating real-time network models of cognitive processing are described and applied.

show abstract

“…Visual input is known to have dramatic effects on the organization of the cortex 23 , a process which has also been demonstrated in self-organizing models 3,24,25 .…”

Section: Spontaneous Retinal Wavesmentioning

confidence: 84%

Pattern-Generator-Driven Development in Self-Organizing Models

Bednar

Miikkulainen

1998

Computational Neuroscience

View full text Add to dashboard Cite

Self-organizing models develop realistic cortical structures when given approximations of the visual environment as input. Recently it has been proposed that internally generated input patterns, such as those found in the developing retina and in PGO waves during REM sleep, may have the same effect. Internal pattern generators would constitute an efficient way to specify, develop, and maintain functionally appropriate perceptual organization. They may help express complex structures from minimal genetic information, and retain this genetic structure within a highly plastic system. Simulations with the RF-LISSOM orientation map model indicate that such preorganization is possible, providing a computational framework for examining how genetic influences interact with visual experience.

show abstract

Self-organization of orientation sensitive cells in the striate cortex

Cited by 1,313 publications

References 18 publications

Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks

Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks

Competitive learning: From interactive activation to adaptive resonance

Pattern-Generator-Driven Development in Self-Organizing Models

Contact Info

Product

Resources

About