A Self-Organizing Neural Network Model of the Primary Visual Cortex

Risto Miikkulainen, James Bednar, Yoonsuck Choe, Joseph Sirosh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Based on recent experimental results on the connectivity and plasticity of the visual cortex, a new theory of the visual cortex has started to emerge. The visual cortex appears to be a continuouslyadapting structure in a dynamic equilibrium with both the external and intrinsic input. This equilibrium is maintained by cooperative and competitive interactions within the cortex, mediated by lateral connections. With the advent of parallel supercomputers in the past few years, it has become viable to test theories about these mechanisms computationally. This paper describes a computational model of the primary visual cortex called RF-SLISSOMthat shows how the observed receptive fields, columnar organization, and lateral connectivity can arise through input-driven Hebbian self-organization, and how such plasticity can account for partial recovery following retinal and cortical lesions. The self-organized network forms a redundancy-reduced sparse coding of the input, which allows it to process massive amounts of information efficiently. The selforganized model can then be used to model various low-level visual phenomena, including tilt aftereffects and segmentation and binding.
Original languageEnglish
Title of host publicationProceedings of the Fifth International Conference on Neural Information Processing (ICONIP'98), Volume 2
EditorsS. Usui, T. Omori
Number of pages4
Publication statusPublished - 1998


Dive into the research topics of 'A Self-Organizing Neural Network Model of the Primary Visual Cortex'. Together they form a unique fingerprint.

Cite this