Big Blue simulates a brain-like computer

BOFFINS AT BIG BLUE say IBM is one step closer to creating a computer that works like the human brain.

That has been the holy grail for artificial intelligence designers because the human brain does some things quite well.

IBM's cognitive computing team claims to have achieved significant advances in large-scale cortical simulation and developed an innovative algorithm that synthesizes neurological data.

Based at Almaden Labs, researchers have performed the first near real-time cortical simulation of a brain that contains 1 billion spiking neurons and 10 trillion individual learning synapses.

The algorithm uses the Blue Gene supercomputing architecture in order to noninvasively measure and map the connections between all cortical and sub-cortical locations within the human brain using magnetic resonance diffusion weighted imaging.

Mapping the wiring diagram of the brain is crucial to untangling its vast communication network and understanding how it represents and processes information, the IBM scientists explain.

This advance gives the world a workbench for exploring the computational dynamics of the brain, and stands to move the IBM team closer to its goal of building a compact, low-power synaptronic chip using nanotechnology and advances in phase change memory and magnetic tunnel junctions.

Josephine Cheng, IBM Fellow and lab director of IBM Research, said that learning from the human brain is an attractive way to overcome power and density challenges faced in computing today.

Obviously Big Blue isn't simulating the brain of a booze soaked hack first thing on a Monday morning because IBM expects its computers to quickly interpret and act on complex tasks. µ