Framework for the evolution of electronic neural assemblies toward directed goals
View Patent ↗Methods and systems for the evolution of electronic neural assemblies toward directed goals. A compact computing architecture includes electronics that allows users of such an architecture to create autonomous agents, in a real or a virtual world and add intelligence to machines. An intelligent machine is composed of four basic modules: one or more sensors, one or more motors, a (Reward Input Output System) RIOS, and a cortex. A number of genetically evolved detectors can project both to cortex and RIOS. At first the neurons within the cortex evolve to predict the structure of the sensory data followed by the structure of proprioceptive activations of its own motor system. Finally, once the cortex has learned its sensory and motor programs, it evolves to predict the reward signals, which comes in multiple channels but is dominated by the detection of the acquisition of free-energy.
1. A system for the evolution of extrinsic logic states, said system comprising:
a processor and a memory that communicate with one another;
a collection of interacting nodes operating an anti-hebbian and hebbian plasticity rule such that said collection of interacting nodes is susceptible to thermodynamic noise in the absence of a positive feedback reward with respect to said anti-hebbian and hebbian plasticity rule, said collection of interacting nodes comprising a module capable of occupying computationally complete attractor states; and
a collection of interacting modules comprising a network that configures itself based on an application of said positive feedback reward, wherein said collection of interacting modules and said collection of interacting nodes communicate and interact with said processor and said memory.
2. The system of claim 1 wherein said positive feedback reward with respect to said anti-hebbian and hebbian plasticity rule is gated.
3. The system of claim 2 wherein said positive feedback reward is gated via a prediction of a signal.
4. The system of claim 2 wherein said positive feedback reward is gated via a detection of free energy.
5. The system of claim 2 wherein said positive feedback reward is gated via a detection of a human smile.
6. The system of claim 1 wherein nodes among said collection of interacting nodes compete with each other for said positive feedback reward within said system.
7. The system of claim 4 further comprising at least one sensor for said detection of said free energy.
8. The system of claim of claim 5 further comprising at least one sensor for said detection of said human smile.