Uni-Logo

2020

  • Zaidi, Sheheryar and Zela, Arber and Elsken, Thomas and Holmes, Chris and Hutter, Frank and Teh, Yee Whye (arXiv)(pdf)(slides)(bib)
    Neural Ensemble Search for Performant and Calibrated Predictions
    In: Workshop on Uncertainty and Robustness in Deep Learning (UDL@ICML`20) (2020)
    Oral Presentation (Video presentation)(Code)
  • Elsken, Thomas and Staffler, Benedikt and Metzen, Jan Hendrik and Hutter, Frank (arXiv)(published)(pdf)(bib)
    Meta-Learning of Neural Architectures for Few-Shot Learning
    In: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    Oral Presentation (Top 6%)
  • Schorn, Christoph and Elsken, Thomas and Vogel, Sebastian and Runge, Armin and Guntoro, Andre and Ascheid, Gerd (arXiv)(published)(pdf)(bib)
    Automated design of error-resilient and hardware-efficient deep neural networks
    In: Neural Computing and Applications (2020): 1 - 19
  • Zela, Arber and Elsken, Thomas and Saikia, Tonmoy and Marrakchi, Yassine and Brox, Thomas and Hutter, Frank (arXiv)(published)(pdf)(slides)(bib)
    Understanding and Robustifying Differentiable Architecture Search
    In: International Conference on Learning Representations
    Oral Presentation (Top 7%)

2019

  • Elsken, Thomas and Metzen, Jan Hendrik and Hutter, Frank (arXiv)(pdf)(bib)
    Neural Architecture Search: A Survey
    In: Journal of Machine Learning Research 20.55 (2019): 1-21
  • Elsken, Thomas and Metzen, Jan Hendrik and Hutter, Frank (arXiv)(published)(bib)
    Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution
    In: International Conference on Learning Representations

2018

  • Elsken, Thomas and Metzen, Jan Hendrik and Hutter, Frank (arXiv)(bib)
    Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution
    In: ArXiv e-prints 1804.09081 (2018)

2017

  • Elsken, Thomas and Metzen, Jan Hendrik and Hutter, Frank (arXiv)(pdf)(bib)
    Simple And Efficient Architecture Search for Convolutional Neural Networks
    In: NIPS Workshop on Meta-Learning