Selection navigates a degenerate circuit space: behavioral individuation without structural differentiation in constrained neuroevolution
Year: 2026
Type: preprint
Abstract: Neural degeneracy, the capacity of structurally distinct circuits to perform the same function, is typically studied as an emergent property of biological neural systems. Here we impose it by construction, engineering the conditions that make degeneracy the expected outcome of evolutionary search, and ask what individual-target selection achieves within that degenerate space. We use constrained neuroevolution to evolve 14-neuron recurrent circuits (Dale’s Law, sparse connectivity, quantized weights) replicating the natural navigation behavior of 9 individual mice across 54 independent evolutionary runs. Architectural constraints impose a structural floor: no aggregate circuit statistic differs across mice (0/18 features, all p FDR > 0.47), and this uniformity extends to the topology axis itself: topology distance predicts behavioral distance at no scale, in evolved or random constrained agents alike, and no structural axis carries significant information about behavioral identity (maximum NMI = 0.2173). Yet behavioral individuation is robust: own-mouse fitness error is 33.4% lower than cross-mouse error, and this specialization persists on held-out data. We show that what individual-target selection shapes is not circuit structure but the strength of functional sensitivity commitment: specialists develop roughly 6.4–6.7 × higher sensitivity variance than generalists trained on all mice simultaneously (9/9 mice, mouse-level p = 0.002), despite exploring statistically indistinguishable topological diversity. The particular pathways a circuit commits to carry no shared mouse-specific signature, so behavioral individuation is expressed as a magnitude of functional commitment rather than a structural or pathway fingerprint—degeneracy that operates not just at the structural level but at the level of the computational strategies that implement individual behavior. Author summary Every mouse behaves a little differently from every other mouse. Where does that individuality live in the brain? The intuitive answer is that different behavior must come from differently wired circuits. We tested that assumption directly. We evolved small artificial neural circuits— just 14 neurons, built under biological rules such as Dale’s Law—until each one reproduced the natural exploratory behavior of one specific mouse, repeating the process 54 times across nine mice. The circuits captured their target well: each performed markedly better on the mouse it was evolved for than on any other, and this advantage held on behavior the circuits had never seen. Yet when we examined their wiring, we found nothing. No structural measurement we tried—connection statistics, network topology, representational geometry, or dynamics— could recover which mouse a circuit had been evolved to match. Individuality was robust in behavior and invisible in structure. What did differ was how strongly each circuit committed to particular sensory inputs, and even those pathways were idiosyncratic rather than shared. Individual differences can therefore be carried by the magnitude of functional commitment rather than by any structural signature.
Authors: Pranet Khetan, Aditya Asopa
Institution: Ashoka University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7169777688