Sustaining Evolution for Shallow Embodied Intelligence
Created by W.Langdon from
gp-bibliography.bib Revision:1.8028
- @InProceedings{Langdon:2024:EI,
-
author = "W. B. Langdon and Daniel Hulme",
-
title = "Sustaining Evolution for Shallow Embodied
Intelligence",
-
booktitle = "Proceedings of 2024 International Conference on
Embodied Intelligence, EI-2024",
-
year = "2024",
-
address = "Internet, Cambridge, UK",
-
month = "20-22 " # mar,
-
organisation = "Bio-Inspired Robotics, Cambridge",
-
note = "forthcoming",
-
keywords = "genetic algorithms, genetic programming, genetic
improvement, Perspectives and outlooks, long term
evolution experiment, information theory, entropy,
software robustness, continuous improvement artificial
intelligence, being shallow, shallow mangrove trees,
porous software computer architectures, geometrical
structures",
-
size = "14 pages",
-
abstract = "Lenski's experiments with E. Coli show Biology can
sustain continual evolutionary improvement. However
long term evolutionary experiments (LTEE) with
evolutionary computing find that information theory's
failed disruption propagation (FDP) in deeply nested
genetic programming (GP) hierarchies can greatly slow
adaptation. We propose that researchers aiming at
embodied artificial intelligence should control
software robustness by using porous high surface area
geometrical architectures, perhaps composed of many
shallow mangrove like tree structures intimately linked
to their data rich fitness environment",
-
notes = "
https://embodied-intelligence.org/wp-content/uploads/2024/03/ei24-conference-programme-slides-final-2.pdf
to be Published after the conference.",
- }
Genetic Programming entries for
William B Langdon
Daniel Hulme
Citations