Recombinant dynamical systems
Neural and Evolutionary Computing
2025-05-20 v1 Neurons and Cognition
Abstract
We describe a connectionist model that attempts to capture a notion of experience-based problem solving or task learning, whereby solutions to newly encountered problems are composed from remembered solutions to prior problems. We apply this model to the computational problem of \emph{efficient sequence generation}, a problem for which there is no obvious gradient descent procedure, and for which not all posable problem instances are solvable. Empirical tests show promising evidence of utility.
Cite
@article{arxiv.2505.13409,
title = {Recombinant dynamical systems},
author = {Saul Kato},
journal= {arXiv preprint arXiv:2505.13409},
year = {2025}
}