Imagination Engines, Inc., Home of the Creativity Machine
Home

HOME OF THE CREATIVITY MACHINE 

The Big Bang of Machine Intelligence!

Imagination Engines, Inc., Home of the Creativity Machine
Imagination Engines, Inc., Home of the Creativity Machine
  • IEI Patent Overview

    The simple, elegant, and inevitable path to human level machine intelligence and beyond, the Creativity Machine Paradigm, US Patent 5,659,666 and all subsequent foreign and divisional filings.

AI's Best Bet
LinkedIn
Google Plus 
Research Gate
AI Showcase Meetup 

The IEI Blog is now open for discussion of new business ventures and opportunities!

 

Creativity Machine Based Art

 

Summary - The fundamental generative neural architecture called the "Creativity Machine Paradigm", can operate within all artistic realms. It is based upon the fundamental scientific principle discovered by S. L. Thaler in the mid 70s of dynamically introducing disturbances into a trained neural network so as to induce spurious attractors and confabulations, as governing algorithms (1) monitor the emergent neural activation patterns for utility or value and/or (2) manage such perturbative influences so as to optimize the turnover of useful concepts and/or strategies. He wrote extensively about this effect in the early 90s in the journal Neural Networks and with it theoretically broached the entire gamut of human cognition (waking consciousness, dreaming, hallucination, and near-death experience) using this one powerful principle. In 1997 he received the first of many patents utilizing this fundamental notion.

 

For an excellent review of this general theory of creativity and consciousness, see "The Creativity Machine Paradigm" in Springer's Encyclopedia of Creativity, Invention, Innovation, and Entrepreneurship.

 

Creativity Machine generating faces, 2000Creativity Machine Gnereated Faces 1993Artistic Explorations by Creativity Machines - From the mid 80s to the present, IEI Creativity Machines have been active in just about all areas of artistic creativity. For instance, in 2000, the application shown to right was demonstrated at the Infowarcon Conference in Washington, DC to distinguish the operation of genetic algorithms from the generative neural architectures taught by the IEI patent suite. Tuned to the correct level of synaptic perturbation, the underlying Creativity Machine (CM) begins to generate faces extrapolated well beyond those encountered within its training exemplars. Immediately to the right of the graphical user interface is a genetic algorithm (GA) struggling to create, well, anything more than a blizzard of pixels. To the extreme right is a face generator built in 1993, operating in real time and producing quarter million pixel portraits of imaginary characters. These purely imaginary faces were seeded by dynamically generated spurious attractors within an imagitron induced by internal damage and degradation dealt out by monitoring algorithms, as taught by the extensive IEI patent suite.

Creativity Machine ChoreographyTo the left, a Creativity Machine spontaneously invents a dance sequence after watching a human subject move through just 12 different poses. It does so through simulated brain cell death, thus the title "Death Dance." After just a half hour's invested time, the system generated kinematic sequences involving realistic dance sequences the underlying network had never before directly experienced through training. Ironically, this particular impromptu project was the inspiration for IEI's creative battlefield robots initiative with the U.S. Air Force! In this case, the imagitron is a recurrent network immersed in critical levels of synaptic noise so as to induce the generation of novel motion sequences.

Creativity Machine Generated Tabloid Headlines, 1998The same multi-talented neural architecture made its literary debut in 1998, with the "International Expirer," an all time favorite attraction to the IEI web site in that time frame. Again, as in all Creativity Machine approaches, spurious attractors are induced through transient damage to a trained artificial neural network as other algorithms, preferably other neural networks, watch an extract the very best of the novel patterns produced. Herein, that supervisory net was one trained upon the inventor's sense of humor. Within this same genre, the Creativity Machine produced a much darker message in 1989, when it gloomily reported, "In the end all good men go to earth in one eternal silent night." Obviously in a Christmassy frame of mind, it quipped, "Deck the walls with last year's follies." It wasn't long after that "people in high places" were requesting much longer messages designed to win and influence people on a global scale.

Creativity Machine Composed Music, 2007Finally, Creativity Machines have been able to generate musical compositions entirely from scratch, taking direction from human audiences whose emotions are being monitored through IEI machine vision applications. At the onset of such generate-and-learn cycles, the machine is exploiting the fractal music that is actually intrinsic to untrained neural networks. Thereafter, the system quickly converges toward what many find extremely appealing, especially when they are provided no clue that the music is being spontaneously composed by machine intelligence. (Click the image to left to hear a short music video with Creativity Machine composed music in the background.)

So, to be quite frank, the fundamental principle of all mental output, whether it be scientific or artistic is the result of Creativity Machine Paradigm in the brain, new ideas or action plans that are seeded by transient disturbances to the internal architectures of the brain's cortex. After that, simply add more money and resources to expand the capabilities of these systems.

To read more about the theoretical underpinnings of this technology, see for instance:

Lest we forget..."Daisy, Daisy" from Scientific American, 1993

  • Death of a Gedanken Creature, Journal of Near-Death Studies, 1995 - Graphic description of how virtual experience arises through the destruction of the neural circuitry within a hypothetical creature. This article inspired the Scientific American article, a snippet of which is shown to right.

  • The Death Dream and Near-Death Darwinism, Journal of Near-Death Studies, 1996 - Introduces the notion that Darwin is also at work in shaping our individual near-death experiences.

  • The Emerging Intelligence and Its Critical Look at Us, Journal of Near-Death Studies, 1998 - In response to critique of what is called the "ultimate text" on near-death experience (Death of a Gedanken Creature) a sober picture of future AI is painted.

  • Neural Networks that Create and Discover (1996), PC AI Magazine.

  • The Creativity Machine Paradigm: Withstanding the Argument from Consciousness, APA Newsletters, Volume 11, Number 2, Spring 2012 - In Alan Turing's landmark paper, "Computing Machinery and Intelligence," the famous cyberneticist takes the position that machines will inevitably think, supplied adequate storage, processor speed, and an appropriate program. Herein we propose the solution to the latter prerequisite for contemplative machine intelligence, the required algorithm, illustrating how it weathers the criticism well anticipated by Turing that a computational system can never attain consciousness.

New Page 1



© 1997-2017, Imagination Engines, Inc. | Creativity Machine®, Imagination Engines®, Imagitron®, and DataBots® are registered trademarks of Imagination Engines, Inc.

1550 Wall Street, Ste. 300, St. Charles, MO 63303 • (636) 724-9000