发表机构
University of Neuchâtel; University College Dublin（纳沙泰尔大学; 都柏林大学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究将激活函数发现视为元学习问题，提出13种生物启发策略，发现时间尺度兼容性决定策略成败，昼夜节律策略最快收敛并减半计算量。
AI 中文摘要
间接编码的神经网络可以为单个节点分配不同的激活函数，但正确的函数很少能预先得知。当可用集合仅包含标准单调函数时，奇偶校验等问题变得不可解，然而一个包罗万象的调色板又不如精心策划的调色板表现好。进化应如何发现使用哪些函数？我们将此视为一个元学习问题，设计了13种策略（其中11种受生物适应机制启发，加上基线和神谕对照），在进化过程中修改可用激活函数的集合。每种策略都将一个生物学原理转化为进化算子：例如，受昼夜节律启发的振荡门控按固定时间表将函数循环进出调色板，而受免疫启发的克隆选择则永久保护那些与适应度持续相关的函数。我们在超过3000次运行中评估了所有策略，涵盖奇偶校验和非奇偶校验问题，首先单独进化激活调色板，然后在更难的问题上共同进化每个节点的聚合调色板；使用新种子的独立重复实验确认了一个稳定的高可靠性层级，其中昼夜节律保持其最高排名。生物启发策略与调整后的基线匹配求解率，但收敛速度快达两倍，昼夜节律将总计算量减半。策略排名在不同问题类型间发生逆转，没有策略在所有领域占主导。策略成功在很大程度上由时间尺度兼容性决定：特征时间尺度与进化评估窗口匹配的策略始终优于那些操作过慢的策略。实用指南：将机制的时间尺度与评估预算相匹配。重新缩放最慢的策略完全绕过了振荡障碍：所有九个解决方案都使用非振荡激活函数配合最小或最大聚合解决了奇偶校验问题。
英文摘要
Indirectly encoded neural networks can assign different activation functions to individual nodes, but the right functions are rarely known in advance. When the available set contains only standard monotonic functions, problems like parity become unsolvable, yet an all-inclusive palette underperforms a curated one. How should evolution discover which functions to use? We address this as a meta-learning problem, designing 13 strategies (11 inspired by biological adaptation mechanisms, plus baseline and oracle controls) that modify the set of available activation functions during evolution. Each strategy translates a biological principle into an evolutionary operator: for example, circadian-inspired oscillatory gating cycles functions in and out of the palette on a fixed schedule, while immune-inspired Clonal Selection permanently protects functions that consistently correlate with fitness. We evaluate all strategies across more than 3,000 runs on parity and non-parity problems, first evolving the activation palette alone, then co-evolving a per-node aggregation palette on harder problems; an independent replication with new seeds confirms a stable high-reliability tier, with Circadian holding its top rank. Bio-inspired strategies match the solve rate of a tuned baseline but converge up to twice as fast, with Circadian halving total compute. Strategy rankings reverse across problem types, with no strategy dominating all domains. Strategy success is largely shaped by timescale compatibility: strategies whose characteristic timescale matches the evolutionary evaluation window consistently outperform those that operate too slowly. The practical guideline: match the mechanism's timescale to the evaluation budget. Rescaling the slowest strategy bypasses the oscillatory barrier entirely: all nine solutions solve parity with non-oscillatory activations paired with min or max aggregation.
Comments16 pages, 2 figures, 7 tables. Authors' accepted manuscript; published in Parallel Problem Solving from Nature - PPSN XIX (Springer, Lecture Notes in Computer Science)
Journal refParallel Problem Solving from Nature - PPSN XIX, Lecture Notes in Computer Science, Springer Nature Switzerland, Cham, 2026, pp. 368-383
DOI：10.1007/978-3-032-36217-9_23
