SOURCE-LINKED INTELLIGENCE

Dimensionless Controls of Plasticity Under Alternating Tasks: From Evolutionary Biology to Continual Learning

arXiv · AI, language, vision and robotics · article · Aug 24, 2026 · UTC

Plasticity under changing environments is central to both evolutionary biology and continual learning. Motivated by recent work on genotype--phenotype maps, we study a minimal deep-learning analogue where a network is trained alternately on two Boolean label sets, and ask which biological controls of plasticity survive the translation to gradient descent. Reinterpreting four proposed biological factors as quantities of training dynamics, we find the system reduces to two dimensionless controls: the task disagreement $r$, the fraction of disagreeing labels, and the reach $ηT$, the product of le

Read original source ↗ Open in workspace

recordType

paper

region

Global