形态发生生长递归网络中的活动依赖可塑性
Activity-Dependent Plasticity in Morphogenetically-Grown Recurrent Networks
AI总结：
研究形态发生生长递归网络中Hebbian与反Hebbian可塑性的作用，发现反Hebbian可塑性显著优于Hebbian，且协同进化独立发现该模式，表明反Hebbian优势对小递归网络具有普适性。
摘要：
神经架构搜索的发育方法通过自组织从紧凑基因组生长出功能网络，但所得网络以固定的生长后权重运行。我们在50,000个形态发生生长的递归控制器（CartPole和Acrobot上超过5M种配置）中刻画了Hebbian和反Hebbian可塑性，然后测试协同进化实验——其中可塑性参数编码在基因组中并与发育架构共同进化——是否独立恢复这些模式。我们的刻画显示：（1）对于胜任网络，反Hebbian可塑性显著优于Hebbian（Cohen's d = 0.53-0.64）；（2）遗憾（在最佳固定设置下损失的oracle改进比例）达到52-100%；（3）在非平稳条件下，可塑性的作用从微调转变为真正的适应。协同进化独立发现这些模式：在CartPole上，70%的运行进化出反Hebbian可塑性（p = 0.043）；在Acrobot上，进化发现接近零的eta且符号混合——与刻画完全匹配。随机RNN对照表明，反Hebbian优势对小递归网络具有普适性，但拓扑依赖程度是发育特异的：形态发生生长网络的遗憾比具有匹配拓扑统计的随机图高2-6倍。
英文摘要：
Developmental approaches to neural architecture search grow functional networks from compact genomes through self-organisation, but the resulting networks operate with fixed post-growth weights. We characterise Hebbian and anti-Hebbian plasticity across 50,000 morphogenetically grown recurrent controllers (5M+ configurations on CartPole and Acrobot), then test whether co-evolutionary experiments -- where plasticity parameters are encoded in the genome and evolved alongside the developmental architecture -- recover these patterns independently. Our characterisation reveals that (1) anti-Hebbian plasticity significantly outperforms Hebbian for competent networks (Cohen's d = 0.53-0.64), (2) regret (fraction of oracle improvement lost under the best fixed setting) reaches 52-100%, and (3) plasticity's role shifts from fine-tuning to genuine adaptation under non-stationarity. Co-evolution independently discovers these patterns: on CartPole, 70% of runs evolve anti-Hebbian plasticity (p = 0.043); on Acrobot, evolution finds near-zero eta with mixed signs -- exactly matching the characterisation. A random-RNN control shows that anti-Hebbian dominance is generic to small recurrent networks, but the degree of topology-dependence is developmental-specific: regret is 2-6x higher for morphogenetically grown networks than for random graphs with matched topology statistics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
