HAL Makes His Debut

  • Print Article |
  • Send to a Friend |
  • |
  • Add to Google |

It is the rare person who doesn't know Stanley Kubrick's Story: 2001 a Space Odyssey. For most people, the main character is HAL, a computer with such amazing artificial intelligence (AI). It becomes a deceitful murderer. Of course at the time of the creation of 2001, artificial intelligence was quite artificial and certainly not very intelligent. In the early 1980s Tcat had written a program in the artificial intelligence language LISP, which he called Crystal Ball. The goal was to assist video store owners choose how many copies of the movie they should buy, and when to begin selling them off. Yes, the program worked. Unfortunately, at only 100,000 instructions per second on the IBM PC, it had to run all night long to create one prediction for one title, for one store. If you need it explained, try kubrick2001.

Today, we have Jeff Hawkins, who previously developed the PalmPilot and Treo smart phone releasing an amazing piece of artificial intelligence known as Numenta. There are several factors that make Numenta, nothing short of extraordinary. Numenta replicates the thinking patterns used by the human brain. By observing over space and time, Numenta looks for patterns, and comes up with some really extraordinary suggestions or actions. It does this by using a technique called Hierarchal Temporal Memory (HTM).

Quoting the Numenta website:

Basic Functions of an HTM

The HTM Network as a whole performs two key functions:

* Discover causes. Causes are persistent and repeating structures in the world. An HTM discovers causes by examining its input data to identify recurring spatial and temporal patterns.

* Infer novel causes in its environment. An HTM classifies its input data relative to known causes that it has identified. When an HTM sees a novel input, it determines not only the most likely high-level cause, but also the hierarchy of sub-causes.

Depending on the application, an HTM could also perform these additional functions:

* Make predictions. An HTM compares changes in the incoming data with known sequences, looks for similarities, and predicts events based on the way sequences commonly evolve.

* Direct behavior. An HTM could also operate a broad range of systems.

An HTM Network resembles a Bayesian Probability Network, in which the nodes constantly share information. HTMs exploit a variation of Belief Propagation, an iterative mathematical technique, to force the entire network to settle quickly on a set of mutually consistent beliefs.

If you consider yourself a sophisticated developer, you'll be delighted to know "Numenta is committed to creating and supporting an open, collaborative community of companies and individuals interested in working on HTM systems. Concurrent with the Numenta Platform release, Numenta also has launched developer community tools and training materials." The current version is available from numenta and is currently available for Macintosh, Linux as well as Windows. The Numenta Platform for Intelligent Computing (NuPIC), is certainly not for the casual developer. And the website has for XP or Vista, the pictures demonstration program. If you give it a try, you can certainly see where you can have your own personal HAL on your computer.

Article Rating (4 stars):
  • article full star
  • article full star
  • article full star
  • article full star
  • article no star
Rate this Article:
  • Article Word Count: 507
  • |
  • Total Views: 412
  • |
  • permalink
  • Print Article |
  • Send to a Friend |
  • |
  • Add to Google |
>