Machine Learning for Biological Inference

Machine learning, and deep neural networks in particular, are increasingly being used in a range of data science tasks such as data pre-processing, classification, and dimension reduction. However, these methods are far less commonly used to inform scientific inference (e.g. does x cause y? What is the functional form of this relationship? etc.). In collaboration with Steve Munch and Ben Martin, we have been exploring how techniques and tools from machine learning such as Symbolic Regression and deep neural networks can be used for inference in ecological systems. Some applications include inferring trophic coupling in demography, and inferring immigration/emigration from population time series.

Research in this area:

Martin, B T, S B Munch, and A M Hein. 2018. Reverse-engineering ecological theory from data. Proc. Roy. Soc.