Maya-Morphe: Bioelectric Gradient Fields as Computational Topology Primitives for Self-Organising Neural Architectures

Birla Institute of Technology and Science, Pilani

Indexed indatacite

Abstract

Maya-Morphe Paper 1 introduces morphogenetic computing — a new computational paradigm in which neural network topology self-organises via spatial bioelectric voltage gradient fields, inspired by Michael Levin's work on bioelectric tissue regeneration in planaria flatworms. We formalise Functional Recovery Rate (FRR) as the first evaluation metric for morphogenetic topology repair, and demonstrate through systematic ablation (3 conditions × 4 damage fractions × 3 seeds = 36 trials) that voltage-driven spatial field repair achieves 99.7% mean FRR with 12/12 full recovery across all damage fractions and seeds. A fixed-topology baseline achieves 0.0% FRR — it cannot self-repair by definition. The gap is 99.7…

Citation impact

42
total citations
FWCI
Percentile
References
21
Too recent for citation history.

Authors

1

Topics & keywords

Keywords
  • Metric (unit)
  • Topology (electrical circuits)
  • Network topology
  • Hyperparameter
  • Artificial neural network
  • Constant (computer programming)
  • Field (mathematics)
  • Baseline (sea)
No related works found for this paper.