On the Expressive Power of Overlapping Architectures of Deep Learning

By Or Sharir, Amnon Shashua. 2017

45 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jean Kossaifi
2. Zachary Chase Lipton
3. Anima Anandkumar
4. Noam Razin
5. Tommaso Furlanello
6. Aran Khanna
7. Nadav Cohen
8. Kamyar Azizzadenesheli

Citations in the corpus

• Tensor Regression Networks (2017, methodology): “(2016), for example, use tensor methods as tools of analysis to study the expressive power of CNNs, while the follow up work (Sharir and Shashua, 2018) focuses on the expressive power of overlapping architectures of deep learning.”
• Implicit Regularization in Deep Learning May Not Be Explainable by Norms (2020, background): “[22, 19, 20, 23, 77, 54, 24, 9, 55]), and has also demonstrated promising results in practice (see [18, 21, 78]).”