1 citations · 1 across the 4 of their papers we have counts for
4 papers · 1 filter
Interpretive Efficiency: Information-Geometric Foundations of Data Usefulness
Ronald Katende
Interpretability is central to trustworthy machine learning, yet existing metrics rarely quantify how effectively data support an interpretive representation. We propose Interpreti…
Decentralized Neural Networks for Robust and Scalable Eigenvalue Computation
Ronald Katende
This paper introduces a novel method for eigenvalue computation using a distributed cooperative neural network framework. Unlike traditional techniques that face scalability challe…
Symmetry-Enriched Learning: A Category-Theoretic Framework for Robust Machine Learning Models
Ronald Katende
This manuscript presents a novel framework that integrates higher-order symmetries and category theory into machine learning. We introduce new mathematical constructs, including hy…
Optimizing Neural Network Performance and Interpretability with Diophantine Equation Encoding
Ronald Katende
This paper explores the integration of Diophantine equations into neural network (NN) architectures to improve model interpretability, stability, and efficiency. By encoding and de…