Learn Like a Human

For the past five years, Jeff Hawkins has been working on computer intelligence. Better known as the co-founder of Palm Computing and Handspring, Hawkins has been interested in the similarities and differences between brains and computers for over two decades.

In 2002, with the encouragement of some neuroscientist friends, he created the Redwood Neuroscience Institute. For three years, he worked with about 10 other scientists there on all aspects of neocortical anatomy, physiology, and theory. More than 100 other scientists visited RNI.

By 2004 Hawkins had developed and published a theory of what has come to be called Hierarchical Temporal Memory, but it was still rooted in biology. He wasn't able to turn the biological theory into a practical technology until a colleague, Dileep George, showed how HTM could be modeled on a type of Bayesian network.

George's prototype application was a vision system that recognized line drawings of 50 different objects, independent of size, position, distortion, and noise. Although it wasn't designed to solve a practical problem, it did things no other existing vision system could do.

In 2005, with a theory of the neocortex, a mathematical expression of that theory, and a working prototype, Hawkins created a start-up, Numenta, in Menlo Park, Calif. Numenta has created a software platform that allows anyone to build HTMs for experimentation and deployment. You don't program an HTM as you would a computer; rather you configure it with software tools, then train it by exposing it to sensory data. HTMs thus learn in much the same way that children do.

Carver Mead once said, "If we really understand a system we will be able to build it." Hawkins has built and tested enough HTMs of sufficient complexity to believe that they work, for at least some difficult and useful problems, such as handling distortion and variances in visual images.

The software development toolset that Numenta has released will allow scientists and developers to go much further. Already, researchers in industry, academia, and government are considering how to use HTMs to solve problems in data-rich areas like oil exploration and drug discovery. HTMs may be able to solve such classic problems as speech and visual pattern recognition, meteorology, and financial analysis.

Source: IEEE Spectrum Magazine

Scientists identify blood component that turns bacteria virulent
Scientists from the Scripps Research Institute have discovered the key chemical that signals Bacillus anthracis, the bacterium that causes anthrax, to become lethal. This finding opens up new avenues of exploration for the development of treatments for bacterial infections.
Iconic rings and flares of galaxies created by violent, intergalactic collisions
The bright pinwheels and broad star sweeps iconic of disk galaxies such as the Milky Way might all be the shrapnel from massive, violent collisions with other galaxies and galaxy-size chunks of dark matter, according to a multi-institutional project involving the University of Pittsburgh. Published in the Nov. 20 edition of The Astrophysical Journal, the findings challenge the longstanding theory that the bright extensions and rings surrounding galaxies are the remnants of smaller star clusters that struck a larger, primary galaxy then fragmented.
Scientists Present 'Moving' Theory Behind Bacterial Decision-Making
(PhysOrg.com) -- Biochemists at North Carolina State University have answered a fundamental question of how important bacterial proteins make life-and-death decisions that allow them to function, a finding that could provide a new target for drugs to disrupt bacterial decision-making processes and related diseases.
Two from one: new research maps out evolution of genders from hermaphroditic ancestors
Research from the University of Pittsburgh published in the Nov. 20 edition of Heredity could finally provide evidence of the first stages of the evolution of separate sexes, a theory that holds that males and females developed from hermaphroditic ancestors. These early stages are not completely understood because the majority of animal species developed into the arguably less titillating separate-sex state too long ago for scientists to observe the transition.
Probing question: What is a molecular clock?
It doesn't tick, it doesn't have hands, and it doesn't tell you what time of day it is. But a molecular clock does tell time -- on an epoch scale. The molecular clock, explained S. Blair Hedges, is a tool used to calculate the timing of evolutionary events.
Want to win friends and influence people? Use Facebook and IM, studies suggest
(PhysOrg.com) -- It's an age-old question: How do you get a new acquaintance to like you? Jeff Hancock, associate professor of communication, says that he and his research team have found in two studies that what works in face-to-face communication can also work in the cyber world.
e=mc2: 103 years later, Einstein's proven right
It's taken more than a century, but Einstein's celebrated formula e=mc2 has finally been corroborated, thanks to a heroic computational effort by French, German and Hungarian physicists.
Study shows messiness leads to behavior decline
(AP) -- Does a messy neighborhood make a difference on how people act? It sure does! Graffiti on the walls, trash in the street, bicycles chained to a fence, all resulted in a decline in how people behaved in a series of experiments.

Learn Like a Human

Related stories:

News discussion: