D-Index & Metrics Best Publications

Caglar Gulcehre

DeepMind (United Kingdom)
United Kingdom

D-Index & Metrics D-index (Discipline H-index) only includes papers and citation values for an examined discipline in contrast to General H-index which accounts for publications across all disciplines.

Discipline name Citations Publications World Ranking National Ranking

Rising Stars D-index 32 Citations 40,195 60 World Ranking 963 National Ranking 194

Computer Science D-index 33 Citations 41,738 59 World Ranking 8260 National Ranking 487

Research.com Recognitions

Awards & Achievements

2022 - Research.com Rising Star of Science Award

Overview

What is he best known for?

The fields of study he is best known for:

Artificial intelligence
Machine learning
Artificial neural network

Caglar Gulcehre mainly investigates Artificial intelligence, Recurrent neural network, Artificial neural network, Speech recognition and Machine translation. His studies in Artificial intelligence integrate themes in fields like Computation and Natural language processing. Recurrent neural network and Newton's method are two areas of study in which Caglar Gulcehre engages in interdisciplinary work.

His work on Gradient descent as part of his general Artificial neural network study is frequently connected to Random matrix, Maxima and minima and Saddle point, thereby bridging the divide between different branches of science. His research on Speech recognition frequently links to adjacent areas such as Convolutional neural network. As part of the same scientific family, he usually focuses on Machine translation, concentrating on Phrase and intersecting with Feature, Rule-based machine translation and Evaluation of machine translation.

His most cited work include:

Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation (6387 citations)
Empirical evaluation of gated recurrent neural networks on sequence modeling (4947 citations)
Learning Phrase Representations using RNN Encoder--Decoder for Statistical Machine Translation (3990 citations)

What are the main themes of his work throughout his whole career to date?

Caglar Gulcehre mainly focuses on Artificial intelligence, Reinforcement learning, Recurrent neural network, Artificial neural network and Machine learning. His Artificial intelligence study frequently draws connections between adjacent fields such as Natural language processing. His study in Reinforcement learning is interdisciplinary in nature, drawing from both Domain, Translation and Human–computer interaction.

His Recurrent neural network research includes themes of Algorithm and Pattern recognition. His Artificial neural network research incorporates elements of Speech recognition and Mathematical optimization. Caglar Gulcehre focuses mostly in the field of Machine translation, narrowing it down to topics relating to Phrase and, in certain cases, Feature.

He most often published in these fields:

Artificial intelligence (69.14%)
Reinforcement learning (33.33%)
Recurrent neural network (29.63%)

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Best Publications

Learning Phrase Representations using RNN Encoder--Decoder for Statistical Machine Translation

Kyunghyun Cho;Bart van Merrienboer;Caglar Gulcehre;Dzmitry Bahdanau.
empirical methods in natural language processing (2014)

17427 Citations

Empirical evaluation of gated recurrent neural networks on sequence modeling

Junyoung Chung;Çaglar Gülçehre;KyungHyun Cho;Yoshua Bengio;Yoshua Bengio;Yoshua Bengio.
arXiv: Neural and Evolutionary Computing (2014)

10246 Citations

Theano: A Python framework for fast computation of mathematical expressions

Rami Al-Rfou;Guillaume Alain;Amjad Almahairi.
arXiv: Symbolic Computation (2016)

2052 Citations

Relational inductive biases, deep learning, and graph networks

Peter W. Battaglia;Jessica B. Hamrick;Victor Bapst;Alvaro Sanchez-Gonzalez.
arXiv: Learning (2018)

1900 Citations

Grandmaster level in StarCraft II using multi-agent reinforcement learning.

Oriol Vinyals;Igor Babuschkin;Wojciech M. Czarnecki;Michaël Mathieu.
Nature (2019)

1669 Citations

Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond

Ramesh Nallapati;Bowen Zhou;Cicero Nogueira dos santos;Caglar Gulcehre.
conference on computational natural language learning (2016)

1621 Citations

Identifying and attacking the saddle point problem in high-dimensional non-convex optimization

Yann N Dauphin;Razvan Pascanu;Caglar Gulcehre;Kyunghyun Cho.
neural information processing systems (2014)

1156 Citations

Gated Feedback Recurrent Neural Networks

Junyoung Chung;Caglar Gulcehre;Kyunghyun Cho;Yoshua Bengio;Yoshua Bengio.
international conference on machine learning (2015)

704 Citations

On using monolingual corpora in neural machine translation

Çaglar Gülçehre;Orhan Firat;Kelvin Xu;Kyunghyun Cho.
arXiv: Computation and Language (2015)

616 Citations

How to Construct Deep Recurrent Neural Networks

Razvan Pascanu;Caglar Gulcehre;Kyunghyun Cho;Yoshua Bengio.
international conference on learning representations (2014)

559 Citations

If you think any of the details on this page are incorrect, let us know.

Frequent Co-Authors

External Links

Personal Website for Caglar Gulcehre