Kybernetica.com > Jeff Hawkins, Neurodudes-style

[neurodudes] It’s not even about a new kind of neural network. It’s about Hawkins’ theory of the cortex, and it is truly revolutionary (whether it’s accurate or not). The idea is that every region of the cortex — visual, auditory, motor, association, language — does the same thing: detection of patterns, representation of invariances, and prediction from a generative model of the world based on invariances. He has a theory of how this is accomplished in each individual cortical column using the cells in the 6 layers.

Previous [Previous] Artificial Intelligence...

Next [Next] Nazi Nuke? Or Platinum Thrillhammer?...

Some slightly related from Technorati and Google.

[Psyplexus.com] Neurobiology : People: Experimental and theoretical studies of sensory processing and sensory motor integration in the mammalian cortex under natural conditions.Thus, I investigate the role of top-down signals, their relation to the fast dynamics, learning and plasticity in the neuronal network. Insights obtained from this work are transferred to real-world applications.

[Oz-atwork.com] SEO-Z=DMOZ: » Eero Simoncelli - The laboratory addresses a variety of basic issues in the analysis and representation of visual imagery. 1) construction of mathematical theories for the representation of visual information, 2) development of functional models for biological visual processing, and 3) creation of novel algorithms for image processing and computer vision applications.

[Freelance-help.com] Open Directory Project > Science> Biology> Neurobiology> People>: Eero Simoncelli - The laboratory addresses a variety of basic issues in the analysis and representation of visual imagery. 1) construction of mathematical theories for the representation of visual information, 2) development of functional models for biological visual processing, and 3) creation of novel algorithms for image processing and computer vision applications.

[Web.mit.edu] Stephen Larson's Research Notebook: Self-organizing maps The major themes behind this bit ofresearch was the discovery of brain-plausible mechanisms fororganizing high-dimensional information. The big deal here seems tobe a good way of capturing invariances about things that appear to betoo invariant to actually be the same thing. A lot of research showsthat SOM's can be used as really good filters for different things ina visual field. It also has the interesting biological aspect ofplacing things that are similar in proximate locations to one another.This ought to be a good thing, but more investigation is needed todecipher why this would be necessary.

[Loandir.net] Catalogue: Eero Simoncelli - The laboratory addresses a variety of basic issues in the analysis and representation of visual imagery. 1) construction of mathematical theories for the representation of visual information, 2) development of functional models for biological visual processing, and 3) creation of novel algorithms for image processing and computer vision applications.

Reflected tags on Technorati: Blog, ,