I am on the 2022-2023 job market! Email is the best way to reach me.
Research: I am a machine learning researcher specializing in deep learning and computer vision. My goal is to understand how we should combine machine learning algorithms and human experts to address important real-world challenges. I am currently working on two facets of this problem. First, I design algorithms for distilling valuable knowledge from real-world data, meaning large amounts of raw data with limited, noisy, and weak supervision. Second, I collaborate with doctors, ecologists, and other domain experts to develop application-inspired benchmarks that test algorithms under realistic conditions and challenge traditional machine learning paradigms.
Previously: I graduated from Duke University in 2017 with a B.S.E. in Electrical and Computer Engineering and Mathematics. I've also spent time at Google Research, Microsoft Research, the Air Force Research Lab, the Duke University Marine Lab, and the Woods Hole Oceanographic Institution. I'm a proud product of public schools in Utah (Grantsville, Sandy, Salt Lake City), Nebraska (Omaha), and Texas (San Antonio).
My work is supported in part by an NSF Graduate Research Fellowship and an Explorer Grant from the Resnick Sustainability Institute.
Joint Implicit Neural Representations for Global-Scale Species Mapping
Elijah Cole, Grant Van Horn, Christian Lange, Alexander Shepard, Patrick Leary, Pietro Perona, Scott Loarie, Oisin Mac Aodha
TLDR: Implicit neural representations for jointly estimating the spatial range of thousands of species from sparse data, with new benchmarks.
On Label Granularity and Object Localization
Elijah Cole, Kimberly Wilber, Grant Van Horn, Xuan Yang, Marco Fornoni, Pietro Perona, Serge Belongie, Andrew Howard, Oisin Mac Aodha
TLDR: Increasing the accuracy and data efficiency of weakly supervised object localization by using coarse-grained labels.
Benchmarking Representation Learning for Natural World Image Collections
Grant Van Horn, Elijah Cole, Sara Beery, Kimberly Wilber, Serge Belongie, Oisin Mac Aodha
CVPR 2021 (Oral)
TLDR: New benchmarks for self-supervised learning grounded in realistic fine-grained ecology tasks.
Paper Code+Data Video
Species Distribution Modeling for Machine Learning Practitioners: A Review
Sara Beery*, Elijah Cole*, Joseph Parker, Pietro Perona, Kevin Winner
ACM COMPASS 2021
TLDR: A review paper to help ML researchers learn about one of the most important problems in ecology and conservation.