2 papers
cs.LG2025
Explanation Beyond Intuition: A Testable Criterion for Inherent Explainability
Michael Merry, Pat Riddle, Jim Warren
Inherent explainability is the gold standard in Explainable Artificial Intelligence (XAI). However, there is not a consistent definition or test to demonstrate inherent explainabil…
cs.LG2024
PropNEAT -- Efficient GPU-Compatible Backpropagation over NeuroEvolutionary Augmenting Topology Networks
Michael Merry, Patricia Riddle, Jim Warren
We introduce PropNEAT, a fast backpropagation implementation of NEAT that uses a bidirectional mapping of the genome graph to a layer-based architecture that preserves the NEAT gen…