RTOP: A Conceptual and Computational Framework for General Intelligence

TL;DR

This paper introduces RTOP, a comprehensive framework for general intelligence that integrates multiple learning types, perception, language, and decision-making processes into a unified model.

Contribution

It presents a novel conceptual and computational model for general intelligence, emphasizing raw, generalized, and innovative learning mechanisms.

Findings

Development of a unified model for multiple learning types

Formation of perception and language through associations

Mechanisms for generalization and innovative thought

Abstract

A novel general intelligence model is proposed with three types of learning. A unified sequence of the foreground percept trace and the command trace translates into direct and time-hop observation paths to form the basis of Raw learning. Raw learning includes the formation of image-image associations, which lead to the perception of temporal and spatial relationships among objects and object parts; and the formation of image-audio associations, which serve as the building blocks of language. Offline identification of similar segments in the observation paths and their subsequent reduction into a common segment through merging of memory nodes leads to Generalized learning. Generalization includes the formation of interpolated sensory nodes for robust and generic matching, the formation of sensory properties nodes for specific matching and superimposition, and the formation of group nodes for simpler logic pathways. Online superimposition of memory nodes across multiple predictions, primarily the superimposition of images on the internal projection canvas, gives rise to Innovative learning and thought. The learning of actions happens the same way as raw learning while the action determination happens through the utility model built into the raw learnings, the utility function being the pleasure and pain of the physical senses.