arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.15869nlin.AOnlin.CD
收藏

进化胜过随机机会:用于增强计算能力的性能依赖型网络进化

Evolution beats random chance: Performance-dependent network evolution for enhanced computational capacity

Manish Yadav, Sudeshna Sinha, Merten Stender

AI总结:

研究提出性能依赖型网络进化框架,利用储备池计算原理生成任务特定最小网络结构,发现其优于随机网络并遵循标度律,为网络结构-功能关系及复杂信息处理机制优化提供新见解。

摘要:

跨科学学科理解网络中结构-功能关系的探索日益深入。然而,最优网络架构仍然难以捉摸,特别是在复杂信息处理方面。因此,我们利用reservoir computing(储备池计算)原理,通过一种性能依赖型网络进化的全新框架,研究了最优且特定的网络结构如何形成以高效解决不同任务。我们的研究表明,通过该框架获得的任务特定最小网络结构,其性能始终优于由其他生长策略生成的网络以及Erdős-Rényi随机网络。进化后的网络表现出意想不到的稀疏性,并在节点密度空间中遵循标度律,同时在输入和信息读出节点分布上展示出独特的不对称性。因此,我们提出了一种启发式方法,用于从性能依赖型进化网络中量化任务复杂度,为网络结构-功能关系的进化动力学提供了有价值的见解。我们的发现不仅推进了对过程特定网络进化的基本理解,也为复杂信息处理机制的设计与优化提供了启示,尤其是在机器学习领域。

英文摘要:

The quest to understand structure-function relationships in networks across scientific disciplines has intensified. However, the optimal network architecture remains elusive, particularly for complex information processing. Therefore, we investigate how optimal and specific network structures form to efficiently solve distinct tasks using a novel framework of performance-dependent network evolution, leveraging reservoir computing principles. Our study demonstrates that task-specific minimal network structures obtained through this framework consistently outperform networks generated by alternative growth strategies and Erdős-Rényi random networks. Evolved networks exhibit unexpected sparsity and adhere to scaling laws in node-density space while showcasing a distinctive asymmetry in input and information readout nodes distribution. Consequently, we propose a heuristic for quantifying task complexity from performance-dependently evolved networks, offering valuable insights into the evolutionary dynamics of network structure-function relationships. Our findings not only advance the fundamental understanding of process-specific network evolution but also shed light on the design and optimization of complex information processing mechanisms, notably in machine learning.

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。

↑