Graham Taylor
University of Guelph professor and Vector Institute faculty member building deep learning for biodiversity
- Professor and Canada Research Chair in Machine Learning, University of Guelph12
- Faculty Member, Vector Institute12
Graham Taylor is a Professor and Canada Research Chair in Machine Learning at the University of Guelph, where Taylor leads the Machine Learning Research Group and co-directs the Centre for Advancing Responsible and Ethical AI (CARE-AI), and a faculty member at the Vector Institute. The group develops deep learning methods spanning generative modelling, multimodal representation learning across images, DNA, and text, graph neural networks, and uncertainty quantification, much of it motivated by monitoring biodiversity. Taylor's CV lists a postdoctoral fellowship at New York University's Courant Institute from 2009 to 2012 and a 2018–2019 term as Visiting Faculty at Google Brain. Taylor is a co-author of BIOSCAN-5M, a multimodal insect dataset that pairs specimen images with DNA barcode sequences and taxonomic labels.123
Work
BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity (external site: arxiv.org)Published research
Co-author of the paper presenting BIOSCAN-5M (journal reference NeurIPS 2024), with benchmark experiments that include pretraining a masked language model on DNA barcode sequences.31
Earlier roles
- Postdoctoral Fellow, Courant Institute of Mathematical Sciences (2009–2012), New York University2
- Visiting Faculty, Google Brain (2018–2019), Google2
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.