People

Amir-Hossein Karimi
Max Planck Institute for Intelligent Systems
E: amirhkarimi@gmail.com
T: @amirhkarimi_
About me
Amir-Hossein Karimi is a PhD student at the Max Planck ETH Center for Learning Systems, supervised by Prof. Dr. Schölkopf and Prof. Dr. Valera. His work focuses on the intersection of causal and explainable machine learning, primarily on the problem of algorithmic recourse, that is, how to help individuals subject to automated algorithmic systems overcome unfavorable predictions. Amir is supported through the generous support of NSERC, CLS, and Google PhD Fellowships.
Publications
JADE: Joint Autoencoders for Dis-Entanglement Journal Article
In: CoRR, vol. abs/1711.09163, 2017.
Optimal motion planning for parallel robots via convex optimization and receding horizon Journal Article
In: Adv. Robotics, vol. 30, no. 17-18, pp. 1145–1163, 2016.
Key-Value Memory Networks for Directly Reading Documents Inproceedings
In: Su, Jian; Carreras, Xavier; Duh, Kevin (Ed.): Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA, November 1-4, 2016, pp. 1400–1409, The Association for Computational Linguistics, 2016.
Spatio-temporal saliency detection using abstracted fully-connected graphical models Inproceedings
In: 2016 IEEE International Conference on Image Processing, ICIP 2016, Phoenix, AZ, USA, September 25-28, 2016, pp. 694–698, IEEE, 2016.