arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.04929cs.NEcs.LG
收藏

蛋白质通路作为人工神经网络拓扑定向进化的催化剂

Protein pathways as a catalyst to directed evolution of the topology of artificial neural networks

Institute of Evolutionary Biology (CSIC-Universitat Pompeu Fabra)(进化生物学研究所(西班牙高等科研理事会-庞培法布拉大学));Technical University of Crete(克里特技术大学);ATHENA, Industrial Systems Institute(雅典娜工业系统研究所);University of Turin(都灵大学);ISI Foundation(ISI基金会);Telefónica Innovación Digital(西班牙电信数字创新部)

Oscar Lao, Konstantinos Zacharopoulos, Apostolos Fournaris, Rossano Schifanella, Ioannis Arapakis

AI总结:

本文提出人工蛋白质网络(APN),借鉴蛋白质网络的结构与演化机制,通过基因型层面的进化算法操作改进人工神经网络拓扑演化,以弥合语法与语义差距并支持多目标优化。

摘要:

在本文中,我们提出一种人工神经网络(ANNs)演化的范式转变,朝向一种新的生物启发设计,该设计基于蛋白质网络(PNs)的结构特性、相互作用和动力学:人工蛋白质网络(APN)。这引入了当前神经演化(NE)领域最先进方法此前未能实现的若干优势:(1)我们可以从大自然如何经过数百万年进化、在DNA中高效编码蛋白质相互作用中获得启发,从而将我们的APN翻译为硅基DNA。这有助于弥合当前NE方法中观察到的语法与语义之间的差距。(2)我们可以从大自然如何在我们基因中构建网络进行学习,从而允许我们通过进化算法(EA)演化设计新的、更智能的网络。(3)我们可以执行EA交叉/变异操作和演化步骤,直接在网络的基因型上复制自然界中观察到的操作,从而探索和利用表型空间,避免陷入次优解。(4)我们对APN的新定义开辟了利用我们关于不同生物和生物学过程知识的新途径。(5)利用生物启发的编码,我们可以建模更复杂的种群和生态关系(例如病毒-宿主或捕食者-猎物相互作用),从而允许我们针对多个、通常是相互冲突的目标进行优化。

英文摘要:

In the present article, we propose a paradigm shift on evolving Artificial Neural Networks (ANNs) towards a new bio-inspired design that is grounded on the structural properties, interactions, and dynamics of protein networks (PNs): the Artificial Protein Network (APN). This introduces several advantages previously unrealized by state-of-the-art approaches in NE: (1) We can draw inspiration from how nature, thanks to millions of years of evolution, efficiently encodes protein interactions in the DNA to translate our APN to silicon DNA. This helps bridge the gap between syntax and semantics observed in current NE approaches. (2) We can learn from how nature builds networks in our genes, allowing us to design new and smarter networks through EA evolution. (3) We can perform EA crossover/mutation operations and evolution steps, replicating the operations observed in nature directly on the genotype of networks, thus exploring and exploiting the phenotypic space, such that we avoid getting trapped in sub-optimal solutions. (4) Our novel definition of APN opens new ways to leverage our knowledge about different living things and processes from biology. (5) Using biologically inspired encodings, we can model more complex demographic and ecological relationships (e.g., virus-host or predator-prey interactions), allowing us to optimise for multiple, often conflicting objectives.

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。

↑