Implementation and Evaluation of a Gradient Descent-Trained Defensible Blackboard Architecture System
Abstract
A variety of forms of artificial intelligence systems have been developed. Two well-known techniques are neural networks and rule-fact expert systems. The former can be trained from presented data while the latter is typically developed by human domain experts. A combined implementation that uses gradient descent to train a rule-fact expert system has been previously proposed. A related system type, the Blackboard Architecture, adds an actualization capability to expert systems. This paper proposes and evaluates the incorporation of a defensible-style gradient descent training capability into the Blackboard Architecture. It also introduces the use of activation functions for defensible artificial intelligence systems and implements and evaluates a new best path-based training algorithm.
Cite
@article{arxiv.2404.11714,
title = {Implementation and Evaluation of a Gradient Descent-Trained Defensible Blackboard Architecture System},
author = {Jordan Milbrath and Jonathan Rivard and Jeremy Straub},
journal= {arXiv preprint arXiv:2404.11714},
year = {2024}
}