ML-AIM Machine Learning and Artificial Intelligence for Medicine

Research Laboratory led by Prof. Mihaela van der Schaar

    Model Interpretability


  1. A. M. Alaa, M. van der Schaar, "Demystifying Black-box Models with Symbolic Metamodels," Neural Information Processing Systems (NeurIPS), 2019.
  2. K. Ahuja, W. Zame, M. van der Schaar, "Optimal Piecewise Approximations for Model Interpretations," Asilomar Conference on Signals, Systems, and Computers., 2019.
  3. J. Yoon, J. Jordon, M. van der Schaar, "INVASE: Instance-wise Variable Selection using Neural Networks," International Conference on Learning Representations (ICLR), 2019. [Link]
  4. O. Lahav, N. Mastronarde, and M. van der Schaar, "What is Interpretable? Using Machine Learning to Design Interpretable Decision-Support Systems," NIPS Machine Learning for Health Workshop 2018. - Selected as spotlight talk [Link] [Poster]