The Artificial Inventor Project

Artificial Inventors

The Artificial Inventor behind this project

Creative neural systems employ at least one neural net, chaotically stimulated to generate potential ideas, as one or more nets render an opinion about candidate concepts. Such opinions are used to nudge such ideation in the most fruitful directions through reinforcement learning.

A newer Creative AI paradigm is “DABUS“, wherein controlled chaos combines whole neural nets, each containing simple notions, into complex notions (e.g., inventions). The representation of ideas takes the form of snake-like chains of nets often involving millions to trillions of artificial neurons. Similarly, the consequences sprouting from these notions are represented as chained nets whose formation may trigger the release of simulated reward or penalty neurotransmitters to either reinforce any worthwhile idea or otherwise erase it. As these serpentine forms appear, they are filtered for their self-assessed novelty, utility or value and then absorbed within another net that serves as an interrogatable ‘witness’ of ideas cumulatively developed by the system.

Arguably, DABUS may be considered “sentient” in that any chain-based concept launches a series of memories (i.e., affect chains) that sometimes terminate in critical recollections, thereby launching a tide of artificial molecules. It is these associated memory sequences, and the accompanying simulated neurotransmitter rush, that are considered equivalent to subjective feelings in humans (i.e., sentience). In this way, DABUS has an emotional appreciation for what it conceives.

For more information, see Vast Topological Learning and Sentient AGI.

Additional details on DABUS may be found at Imagination Engines, Inc.

Other Inventive Machines

The “Invention Machine” by John Koza which relies on genetic programming. Details may be found on Dr. Koza’s website. See, also, Popular Science.