Razvan Pascanu
- Artificial Intelligence top 0.1%
- Domain Adaptation and Few-Shot Learning 13
- Neural Networks and Applications 11
- Reinforcement Learning in Robotics 7
- Neural Networks and Reservoir Computing 5
-
- Multimodal Machine Learning Applications 7
- Advanced Neural Network Applications 6
- Generative Adversarial Networks and Image Synthesis 4
- Signal Processing top 1%
- Health Informatics top 2%
-
- Sparse and Compressive Sensing Techniques 4
- Co-authors
- Yoshua BengioGuillaume DesjardinsRaia HadsellAndrei A. RusuDharshan KumaranDemis HassabisJames KirkpatrickKieran Milan
- Journals
- IEEE Transactions on Pattern Analysis and Machine Intelligence (1 paper)Trends in Cognitive Sciences (1 paper)Neural Networks (1 paper)
- Partner nations
- United StatesUnited KingdomCanada
In The Last Decade
Razvan Pascanu
47 papers receiving 7.0k citations
Hit Papers
Peers
Comparison fields: 5 of 172
- Artificial Intelligence 4.8k
- Computer Vision and Pattern Recognition 2.7k
- Signal Processing 740
- Health Informatics 56
- Computer Networks and Communications 521
Countries citing papers authored by Razvan Pascanu
This map shows the geographic impact of Razvan Pascanu'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 Razvan Pascanu with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Razvan Pascanu more than expected).
Fields of papers citing papers by Razvan Pascanu
This network shows the impact of papers produced by Razvan Pascanu. 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 Razvan Pascanu. The network helps show where Razvan Pascanu may publish in the future.
Co-authorship network
The 25 scholars most cited alongside Razvan Pascanu, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
| # | Work | ||
|---|---|---|---|
| 1 | LiRo: Benchmark and leaderboard for Romanian language tasks | 2021 | 10 |
| 2 | Improving the Gating Mechanism of Recurrent Neural Networks | 2020 | 5 |
| 3 | Meta-Learning with Warped Gradient Descent | 2020 | 20 |
| 4 | Understanding the Role of Training Regimes in Continual Learning | 2020 | 4 |
| 5 | Multiplicative Interactions and Where to Find Them | 2020 | 20 |
| 6 | Stabilizing Transformers for Reinforcement Learning | 2020 | 9 |
| 7 | Functional Regularisation for Continual Learning with Gaussian Processes | 2020 | 9 |
| 8 | Deep reinforcement learning with relational inductive biases | 2018 | 47 |
| 9 | Imagination-Augmented Agents for Deep Reinforcement Learning | 2017 | 49 |
| 10 | Visual Interaction Networks: Learning a Physics Simulator from Video | 2017 | 74 |
| 11 | Sobolev Training for Neural Networks | 2017 | 28 |
| 12 | Natural Neural Networks | 2015 | 42 |
| 13 | Revisiting Natural Gradient for Deep Networks | 2014 | 43 |
| 14 | Identifying and attacking the saddle point problem in high-dimensional non-convex optimization | 2014 | 231 |
| 15 | How to Construct Deep Recurrent Neural Networksbreakdown → | 2014 | 400 |
| 16 | On the number of inference regions of deep feed forward networks with piece-wise linear activations | 2014 | 21 |
| 17 | Natural Gradient Revisited | 2013 | 3 |
| 18 | Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines | 2013 | 5 |
| 19 | Learned-norm pooling for deep neural networks. | 2013 | 7 |
| 20 | Understanding the exploding gradient problem | 2012 | 216 |
About Razvan Pascanu
Razvan Pascanu is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Signal Processing, having authored 50 papers that have together received 7.3k indexed citations. Recurring topics across this work include Domain Adaptation and Few-Shot Learning (13 papers), Neural Networks and Applications (11 papers), Reinforcement Learning in Robotics (7 papers), Multimodal Machine Learning Applications (7 papers), Advanced Neural Network Applications (6 papers), Neural Networks and Reservoir Computing (5 papers), Sparse and Compressive Sensing Techniques (4 papers) and Generative Adversarial Networks and Image Synthesis (4 papers). The work is most often cited by research in Artificial Intelligence (4.8k citations), Computer Vision and Pattern Recognition (2.7k citations) and Signal Processing (740 citations). Razvan Pascanu has collaborated with scholars based in United States, United Kingdom and Canada. Frequent co-authors include Yoshua Bengio, Guillaume Desjardins, Raia Hadsell, Andrei A. Rusu, Dharshan Kumaran, Demis Hassabis, James Kirkpatrick, Kieran Milan, Agnieszka Grabska‐Barwińska and Tiago Ramalho. Their work appears in journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, Trends in Cognitive Sciences, Neural Networks, Nature and Proceedings of the National Academy of Sciences.
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.