Coherence Net - A New Model of Generative Cognition
Michael O. Vertolli, Jim Davies
2014
Abstract
We propose a new algorithm and formal description of generative cognition in terms of the multi-label bag-of-words paradigm. The algorithm, Coherence Net, takes its inspiration from evolutionary strategies, genetic programming, and neural networks. We approach generative cognition in spatial reasoning as the decompression of images that were compressed into lossy feature sets, namely, conditional probabilities of labels. We show that the globally parallel and locally serial optimization technique described by Coherence Net is better at accurately generating contextually coherent subsections of the original compressed images than a competitive, purely serial model from the literature: Coherencer.
DownloadPaper Citation
in Harvard Style
Vertolli M. and Davies J. (2014). Coherence Net - A New Model of Generative Cognition . In Proceedings of the International Conference on Evolutionary Computation Theory and Applications - Volume 1: ECTA, (IJCCI 2014) ISBN 978-989-758-052-9, pages 308-313. DOI: 10.5220/0005149203080313
in Bibtex Style
@conference{ecta14,
author={Michael O. Vertolli and Jim Davies},
title={Coherence Net - A New Model of Generative Cognition},
booktitle={Proceedings of the International Conference on Evolutionary Computation Theory and Applications - Volume 1: ECTA, (IJCCI 2014)},
year={2014},
pages={308-313},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005149203080313},
isbn={978-989-758-052-9},
}
in EndNote Style
TY - CONF
JO - Proceedings of the International Conference on Evolutionary Computation Theory and Applications - Volume 1: ECTA, (IJCCI 2014)
TI - Coherence Net - A New Model of Generative Cognition
SN - 978-989-758-052-9
AU - Vertolli M.
AU - Davies J.
PY - 2014
SP - 308
EP - 313
DO - 10.5220/0005149203080313