MorphoNAS: EMBRYOGENIC NEURAL ARCHITECTURE SEARCH THROUGH MORPHOGEN-GUIDED DEVELOPMENT
KIBERNETYKA TA SYSTEMNYI ANALIZ · 2026 · 30-49
DOI: 10.34229/kca2522-9664.26.2.3 ↗Kurz gefasst
Fachartikel in der Zeitschrift KIBERNETYKA TA SYSTEMNYI ANALIZ, 2026. Verfasst von M.M. Glybovets und 1 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben.
Abstract (Originalsprache)
A novel MorphoNAS approach is proposed for deterministic neural network growth through morphogen-guided self-organization based on the Free Energy Principle, reaction-diffusion systems, and gene regulatory networks. The developmental model is investigated, where compact genomes encode only morphogen dynamics and threshold-based cellular rules enabling single progenitor cell transformation into complex neural architectures. Full success (100%) is achieved in evolutionary search for genomes generating predefined graph configurations with 8-31 nodes. Minimal functional controllers (6–7 neurons) for the CartPole task are obtained under network size minimization pressure with 94% population success rate. The results demonstrate that biologically plausible developmental rules can serve as an effective mechanism for automated neural architecture search. Keywords: MorphoNAS, morphogenesis, neural architecture search, reaction-diffusion systems, gene regulatory networks, evolutionary algorithms.
Zitieren
APA
Glybovets, M., & Medvid, S. (2026). MorphoNAS: EMBRYOGENIC NEURAL ARCHITECTURE SEARCH THROUGH MORPHOGEN-GUIDED DEVELOPMENT. KIBERNETYKA TA SYSTEMNYI ANALIZ, 30-49. https://doi.org/10.34229/kca2522-9664.26.2.3
Vancouver
Glybovets M, Medvid S. MorphoNAS: EMBRYOGENIC NEURAL ARCHITECTURE SEARCH THROUGH MORPHOGEN-GUIDED DEVELOPMENT. KIBERNETYKA TA SYSTEMNYI ANALIZ. 2026:30-49. doi:10.34229/kca2522-9664.26.2.3
BibTeX
@article{Glybovets2026,
author = {Glybovets, M.M. and Medvid, S.O.},
title = {MorphoNAS: EMBRYOGENIC NEURAL ARCHITECTURE SEARCH THROUGH MORPHOGEN-GUIDED DEVELOPMENT},
journal = {KIBERNETYKA TA SYSTEMNYI ANALIZ},
year = {2026},
pages = {30--49},
doi = {10.34229/kca2522-9664.26.2.3}
}
EUVIMED