Development of an Adaptive Multi-Domain Artificial Intelligence System Built using Machine Learning and Expert Systems Technologies

TL;DR

This paper introduces a hybrid AI system combining expert systems, gradient descent training, and generative AI to enable reasoning in unknown domains, marking a step towards artificial general intelligence.

Contribution

It presents a novel integration of classical expert systems with modern training and generative techniques to develop adaptable reasoning capabilities.

Findings

Demonstrates a mechanism for AI to learn and develop reasoning pathways in new domains.

Uses GAI to generate training data and network structures for the system.

Shows improved decision-making through gradient descent optimization.

Abstract

Producing an artificial general intelligence (AGI) has been an elusive goal in artificial intelligence (AI) research for some time. An AGI would have the capability, like a human, to be exposed to a new problem domain, learn about it and then use reasoning processes to make decisions. While AI techniques have been used across a wide variety of problem domains, an AGI would require an AI that could reason beyond its programming and training. This paper presents a small step towards producing an AGI. It describes a mechanism for an AI to learn about and develop reasoning pathways to make decisions in an a priori unknown domain. It combines a classical AI technique, the expert system, with a its modern adaptation - the gradient descent trained expert system (GDTES) - and utilizes generative artificial intelligence (GAI) to create a network and training data set for this system. These can be created from available sources or may draw upon knowledge incorporated in a GAI's own pre-trained model. The learning process in GDTES is used to optimize the AI's decision-making. While this approach does not meet the standards that many have defined for an AGI, it provides a somewhat similar capability, albeit one which requires a learning process before use.