Skip to content
conftrace_

Eugene Vorontsov

3 papers · 2017–2019 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
🌍 Conference Polyglot · Bronze 🐣 Hot Topic Early Bird 🚀 Conference Pioneer

Venues

AAAI (1) ICML (1) NeurIPS (1)

Top co-authors

Yoshua Bengio (2) Chinnadhurai Sankar (1) Sarath Chandar (1) Samira Ebrahimi Kahou (1) Giancarlo Kerg (1) Chiheb Trabelsi (1) Kyle Goyette (1) Gauthier Gidel (1) Samuel Kadoury (1) Chris Pal (1)

Research topics

Deep Learning (3) Machine Learning (3) Architectures (3) Optimization & Theory (3) Learning Types · Deep Learning (2) Artificial Intelligence (1) Core AI (1) Core Methods (1) Learning Types · Machine Learning (1) Techniques (1)

Keywords

recurrent neural network (3) long-term dependency (3) orthogonal matrix (2) vanishing gradient (2) gradient propagation (1) non-saturating activation (1) non-normal rnn (1) schur decomposition (1) orthogonal rnn (1) transient dynamics (1) sequence modeling (1) synthetic task (1) activation function (1) weight matrix (1) memory mechanism (1)

Papers

Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics NeurIPS 2019 Towards Non-Saturating Recurrent Units for Modelling Long-Term Dependencies AAAI 2019 On orthogonality and learning recurrent networks with long term dependencies ICML 2017