Sunday, March 27, 2005

IBM computing algorithm thinks like an animal

Keywords: IBM, artificial intelligence, algorithm, thinking, vertebrate

"A mathematical model that mimics the behavior of the brain's neocortal minicolumns could one day lead to robots that can 'see' like humans and/or make appropriate decisions when bombarded with sensory information.

The mathematical model created at IBM simulates the behavior of 500,000 minicolumns connected by 400 million connections. With it, 'we were able to demonstrate self-organization' and behavior similar to that seen in the real world, according to Charles Peck of IBM's Biometaphorical Computing team."

Link
Source: KurzweilAI.net

Discuss:
Cognitive Science - tribe.net

See also:
Confabulation: New Theory of Cognition
BlueGene/L doubles up - CTWatch Blog

News:
Artificial intelligence - Google News
Artificial intelligence - Yahoo News
Artificial intelligence - Topix.net

Blogs:
Robotic Nation Evidence
Artificial intelligence - Technorati

Ideas:
How to Program the Global Mind - Minding the Planet
CHI, a Collaborative Human Interpreter - Google Blogoscoped

Scenarios:
Robotic Nation - Marshall Brain

Thinkers:
Singularity Institute for Artificial Intelligence
Ben Goertzel
Stormrider

Audio:
John Smart - Simulation, Agents and Accelerating Change - IT Conversations

Learn:
How Your Brain Works - HowStuffWorks
Brain and Cognitive Sciences - MIT OpenCourseWare
Electrical Engineering and Computer Science - MIT OpenCourseWare

No comments: