Ilya Sutskever
Impact in
- Computer Vision and Pattern Recognition top 0.01%
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Video Surveillance and Tracking Methods
- Multimodal Machine Learning Applications
- Artificial Intelligence top 0.01%
- Topic Modeling
- Natural Language Processing Techniques
- Domain Adaptation and Few-Shot Learning
- Anomaly Detection Techniques and Applications
Papers in
-
- Topic Modeling 9
- Neural Networks and Applications 8
- Natural Language Processing Techniques 6
- Machine Learning and Algorithms 6
- Domain Adaptation and Few-Shot Learning 6
-
- Generative Adversarial Networks and Image Synthesis 11
- Multimodal Machine Learning Applications 5
- Co-authors
- Geoffrey E. Hinton (10 shared papers)Alex Krizhevsky (2 shared papers)Ruslan Salakhutdinov (3 shared papers)Nitish Srivastava (1 shared paper)Kai Chen (1 shared paper)Tomáš Mikolov (1 shared paper)Greg S. Corrado (1 shared paper)Jeff Dean (1 shared paper)
- Journals
- Communications of the ACM (1 paper)Nature (1 paper)Neural Networks (1 paper)Neural Computation (1 paper)Journal of Machine Learning Research (1 paper)
- Partner nations
- CanadaUnited StatesUnited Kingdom
In The Last Decade
Ilya Sutskever
39 papers receiving 90.9k citations
Ilya Sutskever's Hit Papers
Peers
Comparison fields: 5 of 236
- Computer Vision and Pattern Recognition 36.1k
- Artificial Intelligence 41.1k
- Media Technology 5.5k
- Signal Processing 6.6k
- Health Informatics 521
Countries citing papers authored by Ilya Sutskever
This map shows the geographic impact of Ilya Sutskever's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Ilya Sutskever with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Ilya Sutskever more than expected).
Fields of papers citing papers by Ilya Sutskever
This network shows the impact of papers produced by Ilya Sutskever. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Ilya Sutskever. The network helps show where Ilya Sutskever may publish in the future.
Co-authors
The 25 scholars most cited alongside Ilya Sutskever, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
Showing the 20 most-cited of 39 papers — load more, or switch the sort, to bring in the rest.
| # | Work | ||
|---|---|---|---|
| 1 | ImageNet classification with deep convolutional neural networks Hit paper breakdown → | 2017 | 47267 |
| 2 | Dropout: a simple way to prevent neural networks from overfitting Hit paper breakdown → | 2014 | 22645 |
| 3 | Distributed Representations of Words and Phrases and their Compositionality Hit paper breakdown → | 2013 | 10644 |
| 4 | Mastering the game of Go with deep neural networks and tree search Hit paper breakdown → | 2016 | 8793 |
| 5 | On the importance of initialization and momentum in deep learning Hit paper breakdown → | 2013 | 1893 |
| 6 | An Empirical Exploration of Recurrent Network Architectures Hit paper breakdown → | 2015 | 833 |
| 7 | Generating Text with Recurrent Neural Networks Hit paper breakdown → | 2011 | 626 |
| 8 | Addressing the Rare Word Problem in Neural Machine Translation Hit paper breakdown → | 2015 | 390 |
| 9 | Learning Recurrent Neural Networks with Hessian-Free Optimization | 2011 | 300 |
| 10 | Improved Variational Inference with Inverse Autoregressive Flow Hit paper breakdown → | 2016 | 293 |
| 11 | Generative Pretraining From Pixels Hit paper breakdown → | 2020 | 288 |
| 12 | The Recurrent Temporal Restricted Boltzmann Machine Hit paper breakdown → | 2008 | 217 |
| 13 | 2016 | 155 | |
| 14 | Modelling Relational Data using Bayesian Clustered Tensor Factorization | 2009 | 127 |
| 15 | One-Shot Imitation Learning | 2017 | 116 |
| 16 | Learning Multilevel Distributed Representations for High-Dimensional Sequences | 2007 | 110 |
| 17 | 2016 | 89 | |
| 18 | 2008 | 79 | |
| 19 | 2014 | 57 | |
| 20 | On the Convergence Properties of Contrastive Divergence | 2010 | 51 |
About Ilya Sutskever
Ilya Sutskever is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics, Signal Processing and Electrical and Electronic Engineering, having authored 39 papers that have together received 95.2k indexed citations. Recurring topics across this work include Generative Adversarial Networks and Image Synthesis (11 papers), Topic Modeling (9 papers), Neural Networks and Applications (8 papers), Model Reduction and Neural Networks (7 papers), Natural Language Processing Techniques (6 papers), Machine Learning and Algorithms (6 papers), Domain Adaptation and Few-Shot Learning (6 papers) and Multimodal Machine Learning Applications (5 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (36.1k citations), Artificial Intelligence (41.1k citations), Media Technology (5.5k citations), Signal Processing (6.6k citations) and Health Informatics (521 citations). Ilya Sutskever has collaborated with scholars based in Canada, United States and United Kingdom. Frequent co-authors include Geoffrey E. Hinton, Alex Krizhevsky, Ruslan Salakhutdinov, Nitish Srivastava, Kai Chen, Tomáš Mikolov, Greg S. Corrado, Jeff Dean, James Martens and Timothy Lillicrap. Their work appears in journals such as Communications of the ACM, Nature, Neural Networks, Neural Computation and Journal of Machine Learning Research.
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.