Joost van Amersfoort

• Personal Webpage
• GitHub
• Twitter
• Google Scholar

Machine Learning, Variational Inference, Uncertainty Estimation

Joost was a DPhil student supervised by Yee Whye Teh and Yarin Gal. He is interested in uncertainty estimation, representation learning, variational inference, and its applications to for example active learning. Previously, he spent two years as a Research Engineer at Twitter’s machine learning team Cortex as part of the team that came out of the Magic Pony acquisition. He obtained his MSc. at the University of Amsterdam, working with Max Welling and Diederik Kingma. He is an Oxford-Google DeepMind scholar.

Publications

2020

• J. Amersfoort , L. Smith , Y. W. Teh , Y. Gal , Uncertainty Estimation Using a Single Deep Deterministic Neural Network, International Conference on Machine Learning, 2020.
  

  @article{van2020uncertainty,
    title = {Uncertainty Estimation Using a Single Deep Deterministic Neural Network},
    author = {van Amersfoort, Joost and Smith, Lewis and Teh, Yee Whye and Gal, Yarin},
    booktitle = {International Conference on Machine Learning},
    year = {2020}
  }
  

2019

• A. Kirsch , J. Amersfoort , Y. Gal , BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning, Advances in Neural Information Processing Systems, 2019.
  

  @article{kirsch2019batchbald,
    title = {BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning},
    author = {Kirsch, Andreas and van Amersfoort, Joost and Gal, Yarin},
    booktitle = {Advances in Neural Information Processing Systems},
    year = {2019}
  }