Saved in:
Bibliographic Details
Main Authors: Milbrath, Jordan, Rivard, Jonathan, Straub, Jeremy
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.11714
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910414401437696
author Milbrath, Jordan
Rivard, Jonathan
Straub, Jeremy
author_facet Milbrath, Jordan
Rivard, Jonathan
Straub, Jeremy
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_11714
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Implementation and Evaluation of a Gradient Descent-Trained Defensible Blackboard Architecture System
Milbrath, Jordan
Rivard, Jonathan
Straub, Jeremy
Artificial Intelligence
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.
title Implementation and Evaluation of a Gradient Descent-Trained Defensible Blackboard Architecture System
topic Artificial Intelligence
url https://arxiv.org/abs/2404.11714