Publications

Publications by year in reversed chronological order. Equal contribution indicated by *. Generated by jekyll-scholar.

2023

  1. Pathologies of predictive diversity in deep ensembles
    Taiga Abe, E Kelly Buchanan, Geoff Pleiss, and John P Cunningham
    arXiv preprint arXiv:2302.00704, 2023
    HTML

2022

  1. Deep ensembles work, but are they necessary?
    Taiga Abe*, E Kelly Buchanan*, Geoff Pleiss, Richard Zemel, and John P Cunningham
    In Advances in Neural Information Processing Systems, 2022
    HTML
  2. Neuroscience Cloud Analysis As a Service: An open-source platform for scalable, peproducible data analysis
    Taiga Abe, Ian Kinsella, Shreya Saxena, E Kelly Buchanan, Joao Couto, John Briggs, Sian Lee Kitt, Ryan Glassman, John Zhou, Liam Paninski, and  others
    Neuron, 2022
    HTML Code
  3. The best deep ensembles sacrifice predictive diversity
    Taiga Abe*, E Kelly Buchanan*, Geoff Pleiss, and John Patrick Cunningham
    In I Can’t Believe It’s Not Better Workshop: Understanding Deep Learning Through Empirical Falsification, 2022
    HTML

2020

  1. Inverse articulated-body dynamics from video via variational sequential Monte Carlo
    Dan Biderman, Christian A Naesseth, Luhuan Wu, Taiga Abe, Alice C Mosberger, Leslie J Sibener, Rui Costa, James Murray, and John P Cunningham
    In First Workshop on Differentiable Computer Vision, Graphics and Physics Applied to Machine Learning, 2020
    HTML

2018

  1. DeepLabCut: markerless pose estimation of user-defined body parts with deep learning
    Alexander Mathis, Pranav Mamidanna, Kevin M Cury, Taiga Abe, Venkatesh N Murthy, Mackenzie Weygandt Mathis, and Matthias Bethge
    Nature Neuroscience, 2018
    HTML