mlsanityData to 14 Oct 2026

Implementation and Evaluation of a Gradient Descent-Trained Defensible Blackboard Architecture System

arXiv 2404.11714 ↗First posted 17 Apr 2024cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 81 references that are in the map. First posted on arXiv 17 Apr 2024.

Builds on

10 of 81 references.

References · 10

  1. 2016An overview of gradient descent optimization algorithmscited by 1,033
  2. 2020Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Losscited by 268
  3. 2017Machine learning methods for histopathological image analysiscited by 79
  4. 2019Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attackscited by 79
  5. 2020Explainable Artificial Intelligence: a Systematic Reviewcited by 79
  6. 2021A Survey of Machine Learning for Computer Architecture and Systemscited by 53
  7. 2019Adaptively Truncating Backpropagation Through Time to Control Gradient Biascited by 22
  8. 2020Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descentcited by 18
  9. 2019A systematic review of fuzzing based on machine learning techniquescited by 8
  10. 2021Expert System Gradient Descent Style Training: Development of a Defensible Artificial Intelligence Techniquecited by 5

Built on by

Not cited yet.