Neutrality and epistasis in program space
Neutrality and epistasis in program space
复制标题
程序空间的中立性和上位性
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
S. Forrest
中科院分区：
文献类型：
--
作者：
J. Renzullo;Westley Weimer;M. Moses;S. Forrest
生物学中的神经网络通常包含具有相同适应度的不同解决方案，当环境（需求）随时间变化时，这可能很有用。在本文中，我们提出了一种在软件中学习神经网络的方法。在这些网络中，我们发现了针对保留测试用例（潜在错误）的多种解决方案，这表明中立软件网络也表现出相关的多样性。我们还观察到随机突变之间的正上位性，即共同增加适应性的相互作用。正上位性作为总搜索空间的一部分是罕见的，但作为目标空间的一部分是重要的：我们发现的9%的修复（在所有分析的程序中为4.63%）是由突变之间的正相互作用产生的。此外，大多数（62.50%）独特的修复是正上位性的情况。
Neutral networks in biology often contain diverse solutions with equal fitness, which can be useful when environments (requirements) change over time. In this paper, we present a method for studying neutral networks in software. In these networks, we find multiple solutions to held-out test cases (latent bugs), suggesting that neutral software networks also exhibit relevant diversity. We also observe instances of positive epistasis between random mutations, i.e. interactions that collectively increase fitness. Positive epistasis is rare as a fraction of the total search space but significant as a fraction of the objective space: 9% of the repairs we found to look (and 4.63% across all programs analyzed) were produced by positive interactions between mutations. Further, the majority (62.50%) of unique repairs are instances of positive epistasis.