Prof. Amir Globerson
Research work
Our group works on machine learning and its applications. Specifically, we are interested in why deep learning algorithms work, and how they can be used for modeling complex semantics in language and vision.
Areas of interest & scientific knowledge
Computational & Theoretical Neuroscience
Methodology
Machine learningSelected Publications
- Roei Herzig, Moshiko Raboh, Gal Chechik, Jonathan Berant and Amir Globerson, Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction, Advances in Neural Information Processing Systems, 2018. https://arxiv.org/abs/1802.05451
- Alon Brutzkus, Amir Globerson, Eran Malach and Shai Shalev-Shwartz SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data International Conference on Learning Representations (ICLR), 2018. https://arxiv.org/abs/1710.10174.pdf