Michal Moshkovitz

What keeps me up at night these days is building machine learning models that are trustworthy and reliable. I specifically focus on explainable and interpretable machine learning for unsupervised, supervised, and reinforcement learning. I'm thinking about:  

• How can we design explanation methods with guarantees? (e.g., interpretable clustering)

• How can we develop models that simultaneously satisfy several trustworthy goals (e.g., interpretability and robustness)

• How can we evaluate different explanation methods? 

I also have other works, exploring how different constraints affect learning:

• What can be learned with bounded memory?

• What are the implications of online decision-making?

Now you can find me at Bosch center for AI. Before that, I was a postdoc at Tel-Aviv University, hosted by Prof. Yishay Mansour. And before that I was a postdoctoral fellow at the Qualcomm Institute at the University of California, San Diego. I did my Ph.D. at the Edmond & Lily Safra Center for Brain Sciences, Hebrew University of Jerusalem, Israel. I obtained M.Sc. in Computer Science, M.Sc. in Computational Neuroscience, and B.A. in Computer Science.

I was an intern at the Machine Learning for Healthcare and Life Sciences group, IBM Research and the Foundations of Machine Learning group, Google.