Proposal for Parallel Computer Architecture of a Cellular Type Aimed at Development of an Autonomous Learning Machine

Abstract

This parallel computer proposal is based on a three dimensional architecture that is inseparable from the software stored in each of its basic components. The software in each basic component (cell) is an equivalent of cellular DNA, and as it deals with all possible situations in the cell's local environment, it would not need to be replaced frequently. All the "cells" at a given level have the same software, and different software at different levels. The system is asynchronous with fixed connections between levels. Only one module is described, but it is structured so that its output can be used as input to an equivalent module, whose software can be adapted to the needs of the user. The 3D modular architecture permits for creation of sufficiently complex modular system that permits simulation of the modular structure of the brain. It permits autonomous learning and feature extraction necessary for formation of the internal "model of the world", used for comparison with incoming sensory data. As autonomous learning machine needs to function on an internal model of the world, something that this system allows for, the research and development based on this system can help in the creation of a "commonsense-machine".