Phased Pruning in Neural Networks Recapitulates Selectivity–Fragility Trade-Offs in Brain Development

Synaptic pruning refines neural circuits during development, but altered trajectories are implicated in neurodevelopmental disorders. Here, we use a task-gated neural network to show that the timing of pruning critically determines functional outcomes. Networks subjected to aggressive pruning only after an initial period of high connectivity develop enhanced resistance to interfering inputs—achieving near-perfect performance under conflicting task demands—yet exhibit marked fragility to internal noise. In contrast, moderate pruning preserves robustness but allows greater interference. These trade-offs emerge prominently when late pruning follows early overgrowth, providing a buffer for refinement into highly selective circuits. The findings reveal developmental phasing as a key driver of circuit specialization versus resilience, offering a mechanistic explanation for phenotypic duality in disorders such as autism spectrum disorder (where intense focus co-occurs with sensory fragility) and highlighting principles relevant to efficient sparse neural networks.