1 / 15

Self-Organization in a Parametrically Coupled Logistic Map Network: A Model for Information

Self-Organization in a Parametrically Coupled Logistic Map Network: A Model for Information Processing in the Visual Cortex. Presenter : YAN-SHOU SIE Authors: Ramin Pashaie , Student Member, IEEE, and Nabil H. Farhat , Life Fellow, IEEE 2009. TNN. Outlines. Motivation Objectives

nuri
Download Presentation

Self-Organization in a Parametrically Coupled Logistic Map Network: A Model for Information

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Self-Organization in a Parametrically Coupled Logistic Map Network: A Model for Information Processing in the Visual Cortex Presenter: YAN-SHOU SIE Authors: RaminPashaie, Student Member, IEEE, and Nabil H. Farhat, Life Fellow, IEEE2009. TNN

  2. Outlines • Motivation • Objectives • Methodology • Experiments • Conclusions • Comments

  3. Motivation • In brain anatomy, the cerebral cortex is the outermost layer of the cerebrum and part of brain that is the center of unsupervised learning and the seat of higher level brain functions including perception, cognition, and learning of both static and dynamic sensory information. • Such as a visual system of mammals is a unsupervised learning .

  4. Objectives • Study of the dynamics of the cortical patches in this model is the main focus. • Propose a new model seeking to emulate the way the visual cortex processes information and interacts with subcortical areas to produce higher level brain functions is described.

  5. Methodology • ARCHITECTURE OF THE NETWORK OF PARAMETRICALLY COUPLED COMPLEX PROCESSING ELEMENTS (PCLMN) • Netlets: Computational Units of Cortex

  6. Methodology • DYNAMICS OF THE NETWORK

  7. Methodology • Stimulation • Iterations Updates

  8. Methodology • Adaptation

  9. Experiments • Stimulation of a PCLMN With Face Images

  10. Experiments • Stimulation of a Cortical Patch With Images of Nature

  11. Experiments

  12. Experiments

  13. Experiments

  14. Conclusions • The model processing elements are simple have rich dynamics that includes fixed-point attractors as well as periodic and chaotic behavior. • In next step, processing elements were coupled parametrically to form PCLMN. • The new model, produces the sparse codes and computational maps considerably faster than other models reported previously. • This may also be used for further study of a model of this kind to produce other cortical maps.

  15. Comments • Advantages • Can helpful to research visual system of mammals and unsupervised learning. • Applications - unsupervised learning ,etc.

More Related