YerevaNN is a non-profit computer science and mathematics research lab based in Yerevan, Armenia.
Read our guide to deep learning. Last updated: December, 2016
The main topics of our research include:
Visit our blog and GitHub for more.
- Time series prediction on medical data
- A set of benchmarks on MIMIC-III dataset [preprint] [code]
- LSTM-based models for the benchmarks [weights]
- This is a collaboration with USC ISI. Partially funded by ISTC.
- Natural language processing with deep learning
- Developing a joint POS tagger, lemmatizer and dependency parser called JointUD [paper] [code]
- Developing a relation extraction pipeline for biomedical texts [code]
- Reproducing DIIN network for NLI [report] [code]
- Reproducing R-NET network for QA [blogpost] [code]
- This is a collaboration with USC ISI.
- Development of Armenian treebanks
- Developing Eastern Armenian treebank according to the Universal Dependencies specifications [website] [code]
- The first version is included in UD v2.2 [data]
- This is a collaboration with Marat Yavrumyan and Anna Danielyan from Yerevan State University. Partially funded by ANSEF and ISTC.
Hrant Khachatrian / Github
Karen Hambardzumyan /
Tigran Galstyan / Github
Martin Mirakyan / Github
Arshak Minasyan / Github
Past members: Hrayr Harutyunyan, Gor Arakelyan
The easiest way to join YerevaNN is to start working on one of the projects listed on
MLEVN Project Ideas Page.
The handwritten digits in the background are generated by deep convolutional generative adversarial networks [paper] [code]