World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
71
Citations
44558
World Ranking
1723
National Ranking
95

Overview

Razvan Pascanu is a researcher affiliated with DeepMind in the United Kingdom. Their work spans a considerable body of research primarily focused in the field of computer science, with a specialization in artificial intelligence and related subfields. The scientist's research contributions are extensively documented in various academic publications, demonstrating engagement with several interconnected topics within machine learning and neural networks.

The primary area of study for Razvan Pascanu is computer science, with notable subfields including artificial intelligence, computer vision and pattern recognition, materials chemistry, computational theory and mathematics, as well as computer networks and communications. Their research interests also encompass specific topics such as domain adaptation and few-shot learning, multimodal machine learning applications, reinforcement learning in robotics, advanced neural network applications, topic modeling, neural networks and applications, and adversarial robustness in machine learning.

Significant recent publications by Razvan Pascanu include:

  • "Understanding the Impact of Value Selection Heuristics in Scheduling Problems," 2025, arXiv (Cornell University)
  • "Static Analysis of Shape in TensorFlow Programs," 2020, arXiv (Cornell University)
  • "Embracing Change: Continual Learning in Deep Neural Networks," 2020, Trends in Cognitive Sciences
  • "Distral: Robust Multitask Reinforcement Learning," 2025, Oxford University Research Archive (ORA) (University of Oxford)
  • "Understanding the Role of Training Regimes in Continual Learning," 2020, arXiv (Cornell University)

Razvan Pascanu frequently collaborates with several co-authors who have contributed notably to machine learning. Frequent co-authors include Yee Whye Teh, Çaǧlar Gülçehre, Petar Veličković, Soham De, and Jörg Bornschein.

The researcher regularly publishes in prominent venues, predominantly in arXiv (Cornell University), with 80 publications there. Other publication venues include Trends in Cognitive Sciences, IEEE Transactions on Pattern Analysis and Machine Intelligence, Nature, and Oxford University Research Archive (ORA) (University of Oxford).

Best Publications

  • Overcoming catastrophic forgetting in neural networks

    James Kirkpatrick;Razvan Pascanu;Neil C. Rabinowitz;Joel Veness

  • On the difficulty of training recurrent neural networks

    Razvan Pascanu;Tomas Mikolov;Yoshua Bengio

  • Relational inductive biases, deep learning, and graph networks

    Peter W. Battaglia;Jessica B. Hamrick;Victor Bapst;Alvaro Sanchez-Gonzalez

  • Theano: A Python framework for fast computation of mathematical expressions

    Rami Al-Rfou;Guillaume Alain;Amjad Almahairi

  • Theano: A CPU and GPU Math Compiler in Python

    James Bergstra;Olivier Breuleux;Frédéric Bastien;Pascal Lamblin

  • Theano: new features and speed improvements

    Frédéric Bastien;Pascal Lamblin;Razvan Pascanu;James Bergstra

  • A simple neural network module for relational reasoning

    Adam Santoro;David Raposo;David G. T. Barrett;Mateusz Malinowski

  • Progressive neural networks

    Neil Charles Rabinowitz;Guillaume Desjardins;Andrei-Alexandru Rusu;Koray Kavukcuoglu

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

    Yann N Dauphin;Razvan Pascanu;Caglar Gulcehre;Kyunghyun Cho

  • On the Number of Linear Regions of Deep Neural Networks

    Guido F Montufar;Razvan Pascanu;Kyunghyun Cho;Yoshua Bengio

  • Interaction networks for learning about objects, relations and physics

    Peter Battaglia;Razvan Pascanu;Matthew Lai;Danilo Jimenez Rezende

  • How to Construct Deep Recurrent Neural Networks

    Razvan Pascanu;Caglar Gulcehre;Kyunghyun Cho;Yoshua Bengio

  • Meta-Learning with Latent Embedding Optimization

    Andrei A. Rusu;Dushyant Rao;Jakub Sygnowski;Oriol Vinyals

  • Vector-based navigation using grid-like representations in artificial agents

    Andrea Banino;Caswell Barry;Benigno Uria;Charles Blundell

  • Advances in optimizing recurrent networks

    Yoshua Bengio;Nicolas Boulanger-Lewandowski;Razvan Pascanu

  • Learning to Navigate in Complex Environments

    Piotr Mirowski;Razvan Pascanu;Fabio Viola;Hubert Soyer

  • Understanding the exploding gradient problem

    Razvan Pascanu;Tomas Mikolov;Yoshua Bengio

  • Learning Deep Generative Models of Graphs

    Yujia Li;Oriol Vinyals;Chris Dyer;Razvan Pascanu

  • Model compression via distillation and quantization

    Antonio Polino;Razvan Pascanu;Dan Alistarh

  • Malware classification with recurrent networks

    Razvan Pascanu;Jack W. Stokes;Hermineh Sanossian;Mady Marinescu

  • Progress & Compress: A scalable framework for continual learning

    Jonathan Schwarz;Jelena Luketina;Wojciech M. Czarnecki;Agnieszka Grabska-Barwinska

  • Imagination-Augmented Agents for Deep Reinforcement Learning

    Sébastien Racanière;Theophane Weber;David P. Reichert;Lars Buesing

Frequent Co-Authors

Yoshua Bengio
Yoshua Bengio University of Montreal
Raia Hadsell
Raia Hadsell DeepMind (United Kingdom)
Nicolas Heess
Nicolas Heess DeepMind (United Kingdom)
Caglar Gulcehre
Caglar Gulcehre DeepMind (United Kingdom)
Peter W. Battaglia
Peter W. Battaglia DeepMind (United Kingdom)
Yee Whye Teh
Yee Whye Teh University of Oxford
Oriol Vinyals
Oriol Vinyals DeepMind (United Kingdom)
Koray Kavukcuoglu
Koray Kavukcuoglu DeepMind (United Kingdom)
Kyunghyun Cho
Kyunghyun Cho New York University

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

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring online degrees in Computer Science and related fields can open doors to diverse career pathways. Many students are choosing accredited online programs for their flexibility and quality. If you’re interested in reputable options, you can start by reviewing the top 10 online universities to find the best fit for your needs.

Specialized areas within Computer Science, such as game development and cybersecurity, are also gaining popularity. A video game design degree prepares you for creative and technical roles in the booming gaming industry. If protecting digital assets interests you, an online cybersecurity degree online is a practical choice with strong job prospects.

Computer Science also intersects with other fields, such as construction. With increasing reliance on project management software and smart technologies, a construction management degree can broaden your career options, combining tech expertise with leadership in the built environment sector.

Best Scientists Citing Razvan Pascanu

Trending Scientists