Expert System Gradient Descent Style Training: Development of a Defensible Artificial Intelligence Technique

TL;DR

This paper introduces a novel AI training method using expert systems with meaning-assigned nodes and rules, aiming to create more defensible and legally compliant AI decisions.

Contribution

It develops a new training approach for AI systems that incorporates meaning and rules, improving decision defensibility and legal compliance.

Findings

Expert systems outperform random networks in decision quality.

Training with meaning-assigned nodes reduces legal liability risks.

Performance varies with network error and augmentation levels.

Abstract

Artificial intelligence systems, which are designed with a capability to learn from the data presented to them, are used throughout society. These systems are used to screen loan applicants, make sentencing recommendations for criminal defendants, scan social media posts for disallowed content and more. Because these systems don't assign meaning to their complex learned correlation network, they can learn associations that don't equate to causality, resulting in non-optimal and indefensible decisions being made. In addition to making decisions that are sub-optimal, these systems may create legal liability for their designers and operators by learning correlations that violate anti-discrimination and other laws regarding what factors can be used in different types of decision making. This paper presents the use of a machine learning expert system, which is developed with meaning-assigned nodes (facts) and correlations (rules). Multiple potential implementations are considered and evaluated under different conditions, including different network error and augmentation levels and different training levels. The performance of these systems is compared to random and fully connected networks.