A New Framework for Machine Intelligence: Concepts and Prototype

TL;DR

This paper introduces a comprehensive theoretical framework combining Mirror Compositional Representations and a Solution-Critic Loop, aiming to advance general intelligent systems with a prototype for document comparison.

Contribution

It proposes a novel, unified framework for intelligent systems and demonstrates its application through a prototype for document comparison.

Findings

Successful implementation of the prototype system

Framework's potential for diverse problem types

Foundation for future general AI development

Abstract

Machine learning (ML) and artificial intelligence (AI) have become hot topics in many information processing areas, from chatbots to scientific data analysis. At the same time, there is uncertainty about the possibility of extending predominant ML technologies to become general solutions with continuous learning capabilities. Here, a simple, yet comprehensive, theoretical framework for intelligent systems is presented. A combination of Mirror Compositional Representations (MCR) and a Solution-Critic Loop (SCL) is proposed as a generic approach for different types of problems. A prototype implementation is presented for document comparison using English Wikipedia corpus.