otherZenodo (CERN European Organization for Nuclear Research)May 18, 2026GREEN OA

Maya-Morphe P3: Axon — Differentiable Bioelectric Edge Formation via Voltage-Guided Axonal Pathfinding in Morphogenetic Neural Networks

VSVenkatesh Swaminathan

Birla Institute of Technology and Science, Pilani

Indexed indatacite

Abstract

Maya-Morphe P3: Axon is a two-part study extending morphogenetic computing through differentiable bioelectric edge formation. Part 1 (336 trials, 7 scales) confirms the substrate threshold constant ~0.162 scale-invariant across 29,056–266,071 cells using the full AxonNet architecture (VoltageFieldEncoder + LearnableThreshold + EdgeFormationModule). Part 2 (240 trials, 6/7 scales) introduces MATURATION_STEPS=20, enabling recovering cells to form new edges guided by the bioelectric voltage field via Gumbel-Softmax differentiable sampling. We introduce Edge-Field Concordance (EFC) as the first quantitative metric for field-guided connectivity in morphogenetic computing — the Pearson correlation between voltage…

Citation impact

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

Authors

1

Topics & keywords

Keywords
  • Metric (unit)
  • Axon
  • Differentiable function
  • Pathfinding
  • Artificial neural network
  • Enhanced Data Rates for GSM Evolution
  • Topology (electrical circuits)
  • Field (mathematics)
No related works found for this paper.