Razvan Pascanu
Impact in
- Artificial Intelligence top 0.1%
- Domain Adaptation and Few-Shot Learning
- Topic Modeling
- Anomaly Detection Techniques and Applications
- Machine Learning and ELM
- Neural Networks and Applications
-
- Multimodal Machine Learning Applications
- Advanced Neural Network Applications
- Human Pose and Action Recognition
Papers in
-
- Domain Adaptation and Few-Shot Learning 10
- Neural Networks and Applications 7
- Neural Networks and Reservoir Computing 4
-
- Multimodal Machine Learning Applications 4
- Generative Adversarial Networks and Image Synthesis 3
- Advanced Neural Network Applications 3
- Co-authors
- Guillaume Desjardins (3 shared papers)Raia T. Hadsell (4 shared papers)Andrei A. Rusu (3 shared papers)Yoshua Bengio (8 shared papers)Kieran Milan (1 shared paper)Dharshan Kumaran (3 shared papers)James Kirkpatrick (1 shared paper)Agnieszka Grabska‐Barwińska (1 shared paper)
- Journals
- Nature (2 papers)ACM Transactions on Multimedia Computing Communications and Applications (1 paper)Trends in Cognitive Sciences (1 paper)Neural Networks (1 paper)IEEE Transactions on Pattern Analysis and Machine Intelligence (1 paper)
- Partner nations
- United StatesUnited KingdomCanada
In The Last Decade
Razvan Pascanu
31 papers receiving 8.3k citations
Razvan Pascanu's Hit Papers
Peers
Comparison fields: 5 of 174
- Artificial Intelligence 5.3k
- Computer Vision and Pattern Recognition 3.2k
- Signal Processing 895
- Health Informatics 59
- Cognitive Neuroscience 695
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-authors
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
Showing the 20 most-cited of 40 papers — load more, or switch the sort, to bring in the rest.
| # | Work | ||
|---|---|---|---|
| 1 | Overcoming catastrophic forgetting in neural networks Hit paper breakdown → | 2017 | 4665 |
| 2 | Theano: A CPU and GPU Math Compiler in Python Hit paper breakdown → | 2010 | 851 |
| 3 | How to Construct Deep Recurrent Neural Networks Hit paper breakdown → | 2014 | 442 |
| 4 | Vector-based navigation using grid-like representations in artificial agents Hit paper breakdown → | 2018 | 402 |
| 5 | Advances in optimizing recurrent networks Hit paper breakdown → | 2013 | 325 |
| 6 | Malware classification with recurrent networks Hit paper breakdown → | 2015 | 317 |
| 7 | 2020 | 312 | |
| 8 | Combining modality specific deep neural networks for emotion recognition in video Hit paper breakdown → | 2013 | 298 |
| 9 | Learning Algorithms for the Classification Restricted Boltzmann Machine | 2012 | 227 |
| 10 | Theano: Deep Learning on GPUs with Python | 2012 | 143 |
| 11 | 2014 | 122 | |
| 12 | Visual Interaction Networks: Learning a Physics Simulator from Video | 2017 | 90 |
| 13 | Deep reinforcement learning with relational inductive biases | 2018 | 68 |
| 14 | Deep Learners Benefit More from Out-of-Distribution Examples | 2011 | 67 |
| 15 | 2010 | 59 | |
| 16 | Sobolev Training for Neural Networks | 2017 | 38 |
| 17 | Multiplicative Interactions and Where to Find Them | 2020 | 28 |
| 18 | Meta-Learning with Warped Gradient Descent | 2020 | 24 |
| 19 | 2011 | 19 | |
| 20 | Linear Mode Connectivity in Multitask and Continual Learning | 2021 | 19 |
About Razvan Pascanu
Razvan Pascanu is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing, Cognitive Neuroscience and Hardware and Architecture, having authored 40 papers that have together received 8.6k indexed citations. Recurring topics across this work include Domain Adaptation and Few-Shot Learning (10 papers), Neural Networks and Applications (7 papers), Multimodal Machine Learning Applications (4 papers), Neural Networks and Reservoir Computing (4 papers), Generative Adversarial Networks and Image Synthesis (3 papers), EEG and Brain-Computer Interfaces (3 papers), Music and Audio Processing (3 papers) and Advanced Neural Network Applications (3 papers). The work is most often cited by research in Artificial Intelligence (5.3k citations), Computer Vision and Pattern Recognition (3.2k citations), Signal Processing (895 citations), Health Informatics (59 citations) and Cognitive Neuroscience (695 citations). Razvan Pascanu has collaborated with scholars based in United States, United Kingdom and Canada. Frequent co-authors include Guillaume Desjardins, Raia T. Hadsell, Andrei A. Rusu, Yoshua Bengio, Kieran Milan, Dharshan Kumaran, James Kirkpatrick, Agnieszka Grabska‐Barwińska, Neil C. Rabinowitz and Demis Hassabis. Their work appears in journals such as Nature, ACM Transactions on Multimedia Computing Communications and Applications, Trends in Cognitive Sciences, Neural Networks and IEEE Transactions on Pattern Analysis and Machine Intelligence.
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.