当前位置: X-MOL 学术Evolution › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
The Camouflage Machine: Optimising protective coloration using deep learning with genetic algorithms
Evolution ( IF 3.1 ) Pub Date : 2021-01-18 , DOI: 10.1111/evo.14162
John G Fennell 1 , Laszlo Talas 1 , Roland J Baddeley 1 , Innes C Cuthill 2 , Nicholas E Scott-Samuel 1
Affiliation  

Evolutionary biologists frequently wish to measure the fitness of alternative phenotypes using behavioural experiments. However, many phenotypes are complex. One example is coloration: camouflage aims to make detection harder, while conspicuous signals (e.g. for warning or mate attraction) require the opposite. Identifying the hardest and easiest to find patterns is essential for understanding the evolutionary forces that shape protective coloration, but the parameter space of potential patterns (coloured visual textures) is vast, limiting previous empirical studies to a narrow range of phenotypes. Here we demonstrate how deep learning combined with genetic algorithms can be used to augment behavioural experiments, identifying both the best camouflage and the most conspicuous signal(s) from an arbitrarily vast array of patterns. To show the generality of our approach, we do so for both trichromatic (e.g. human) and dichromatic (e.g. typical mammalian) visual systems, in two different habitats. The patterns identified were validated using human participants; those identified as the best for camouflage were significantly harder to find than a tried-and-tested military design, while those identified as most conspicuous were significantly easier to find than other patterns. More generally, our method, dubbed the 'Camouflage Machine', will be a useful tool for identifying the optimal phenotype in high dimensional state-spaces. This article is protected by copyright. All rights reserved.

中文翻译:

伪装机:使用遗传算法的深度学习优化保护色

进化生物学家经常希望使用行为实验来衡量替代表型的适合度。然而,许多表型是复杂的。一个例子是着色:伪装旨在使检测更加困难,而显眼的信号(例如警告或配偶吸引)要求相反。识别最难和最容易找到的模式对于理解形成保护色的进化力量至关重要,但潜在模式(彩色视觉纹理)的参数空间是巨大的,将以前的实证研究限制在一个狭窄的表型范围内。在这里,我们展示了如何使用深度学习与遗传算法相结合来增强行为实验,从任意大量的模式中识别出最好的伪装和最显眼的信号。为了显示我们的方法的普遍性,我们在两个不同的栖息地中对三色(例如人类)和二色(例如典型的哺乳动物)视觉系统都这样做。识别出的模式已使用人类参与者进行验证;那些被认为最适合伪装的图案比久经考验的军事设计明显更难找到,而那些被确定为最显眼的图案比其他图案更容易找到。更一般地说,我们的方法,被称为“伪装机器”,将成为识别高维状态空间中最佳表型的有用工具。本文受版权保护。版权所有。识别出的模式已使用人类参与者进行验证;那些被认为最适合伪装的图案比久经考验的军事设计明显更难找到,而那些被确定为最显眼的图案比其他图案更容易找到。更一般地说,我们的方法,被称为“伪装机器”,将成为识别高维状态空间中最佳表型的有用工具。本文受版权保护。版权所有。识别出的模式已使用人类参与者进行验证;那些被认为最适合伪装的图案比久经考验的军事设计明显更难找到,而那些被确定为最显眼的图案比其他图案更容易找到。更一般地说,我们的方法,被称为“伪装机器”,将成为识别高维状态空间中最佳表型的有用工具。本文受版权保护。版权所有。将是识别高维状态空间中最佳表型的有用工具。本文受版权保护。版权所有。将是识别高维状态空间中最佳表型的有用工具。本文受版权保护。版权所有。
更新日期:2021-01-18
down
wechat
bug