Nadav Cohen
News
Research
My research focuses on the theoretical and algorithmic foundations of deep learning. In particular, I am interested in the application of tensor analysis for the study of convolutional network architectures.
Yoav Levine, David Yakira, Nadav Cohen and Amnon Shashua. Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design. Apr’17.
Nadav Cohen, Ronen Tamari and Amnon Shashua. Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions. Mar’17.
Nadav Cohen and Amnon Shashua. Inductive Bias of Deep Convolutional Networks through Pooling Geometry. May’16 (v1), Nov’16 (v2). ICLR 2017.
Or Sharir, Ronen Tamari, Nadav Cohen and Amnon Shashua. Tensorial Mixture Models. Oct’16.
Nadav Cohen and Amnon Shashua. Convolutional Rectifier Networks as Generalized Tensor Decompositions (extended arXiv version). Mar’16. ICML 2016.
Nadav Cohen, Or Sharir and Amnon Shashua. On the Expressive Power of Deep Learning: A Tensor Analysis. Sep’15 (v1), Feb’16 (v2). COLT 2016.
Nadav Cohen, Or Sharir and Amnon Shashua. Deep SimNets. Jun’15 (v1), Nov’15 (v2). CVPR 2016.
Nadav Cohen and Amnon Shashua. SimNets: A Generalization of Convolutional Networks. Oct’14 (v1), Dec’14 (v2). NIPS 2014 Deep Learning Workshop.
Selected Talks
Mathematics of Deep Learning Workshop 2017 (Berlin): [slides]
AAAI Spring Symposium Series 2017 (Palo Alto): [slides]
CVPR 2017 (Honolulu): [slides]
GAMM 2017 (Weimar): [slides]
NIPS 2016 (Barcelona): [slides]
ICML 2016 (New York City): [videoslides]
COLT 2016 (New York City): [videoslides]
Teaching
