Deep learning as a tool for ecology and evolution

• DOI: 10.32942/osf.io/nt3as
• Publication Date: 2021-06-26T00:13:47Z
• Authors: Marek Borowiec; Paul Frandsen; Rebecca Dikow; Alexander McKeeken; Gabriele Valentini; Alexander White
• Keywords: 0301 basic medicine; 03 medical and health sciences; bepress|Life Sciences; Ecology and Evolutionary Biology; Life Sciences; bepress|Life Sciences|Ecology and Evolutionary Biology

Deep learning is driving recent advances behind many everyday technologies, including those relying on speech and image recognition, natural language processing, autonomous driving. It also gaining popularity in biology, where it has been used for automated species identification, environmental monitoring, behavioral studies, DNA sequencing, population genetics phylogenetics, among other applications. relies artificial neural networks predictive modeling excels at recognizing complex patterns. Operating within the machine paradigm, deep can be viewed as an alternative to likelihood-based inference methods. desirable properties, good performance scaling with increasing complexity, while posing unique challenges such sensitivity bias input data. In this review we provide a gentle introduction learning, its applications ecology evolution, discuss limitations efforts overcome them. We practical primer biologists interested their toolkit identify possible future