World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
40
Citations
21842
World Ranking
9014
National Ranking
554

Overview

Charles Blundell is a researcher affiliated with DeepMind in the United Kingdom. Their work spans the domain of computer science with a strong focus on artificial intelligence and its applications.

The main fields of study for Charles Blundell include:

  • Computer Science

Within computer science, their research emphasizes several subfields, including:

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Cognitive Neuroscience
  • Geometry and Topology
  • Discrete Mathematics and Combinatorics

Charles Blundell's research covers a range of topics such as:

  • Reinforcement Learning in Robotics
  • Domain Adaptation and Few-Shot Learning
  • Topic Modeling
  • Multimodal Machine Learning Applications
  • Artificial Intelligence in Games
  • Advanced Neural Network Applications
  • Neural dynamics and brain function

Their publication record includes papers in notable venues, with frequent contributions to:

  • arXiv (Cornell University)
  • Nature
  • bioRxiv (Cold Spring Harbor Laboratory)
  • Representation Theory of the American Mathematical Society
  • Machine Learning Science and Technology

Recent papers authored or coauthored by Charles Blundell include:

  • Advancing mathematics by guiding human intuition with AI, 2021, Nature
  • Agent57: Outperforming the Atari Human Benchmark, 2020, arXiv (Cornell University)
  • Never Give Up: Learning Directed Exploration Strategies, 2020, arXiv (Cornell University)
  • A model of egocentric to allocentric understanding in mammalian brains, 2020, bioRxiv (Cold Spring Harbor Laboratory)
  • PonderNet: Learning to Ponder, 2021, arXiv (Cornell University)

Frequent co-authors collaborating with Charles Blundell include:

  • Petar Veličković
  • Andrea Banino
  • Adrià Puigdomènech Badia
  • Lars Buesing
  • Borja Ibarz

Best Publications

  • Matching networks for one shot learning

    Oriol Vinyals;Charles Blundell;Timothy Lillicrap;Koray Kavukcuoglu

  • Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles

    Balaji Lakshminarayanan;Alexander Pritzel;Charles Blundell

  • Weight Uncertainty in Neural Network

    Charles Blundell;Julien Cornebise;Koray Kavukcuoglu;Daan Wierstra

  • Weight Uncertainty in Neural Networks

    Charles Blundell;Julien Cornebise;Koray Kavukcuoglu;Daan Wierstra

  • Deep exploration via bootstrapped DQN

    Ian Osband;Charles Blundell;Alexander Pritzel;Benjamin Van Roy

  • PathNet: Evolution Channels Gradient Descent in Super Neural Networks

    Chrisantha Fernando;Dylan Banarse;Charles Blundell;Yori Zwols

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

    Andrea Banino;Caswell Barry;Benigno Uria;Charles Blundell

  • Reinforcement Learning, Fast and Slow.

    Matthew Botvinick;Sam Ritter;Jane X. Wang;Zeb Kurth-Nelson

  • Noisy Networks For Exploration

    Meire Fortunato;Mohammad Gheshlaghi Azar;Bilal Piot;Jacob Menick

  • Learning to reinforcement learn

    Jane X. Wang;Zeb Kurth-Nelson;Dhruva Tirumala;Hubert Soyer

  • Advancing mathematics by guiding human intuition with AI.

    Alex Davies;Petar Veličković;Lars Buesing;Sam Blackwell

  • DARLA: improving zero-shot transfer in reinforcement learning

    Irina Higgins;Arka Pal;Andrei Rusu;Loic Matthey

  • Deep AutoRegressive Networks

    Karol Gregor;Ivo Danihelka;Andriy Mnih;Charles Blundell

  • Agent57: Outperforming the Atari Human Benchmark

    Adrià Puigdomenech Badia;Bilal Piot;Steven Kapturowski;Pablo Sprechmann

  • Modelling Reciprocating Relationships with Hawkes Processes

    Charles Blundell;Jeff Beck;Katherine A. Heller

  • Neural Episodic Control

    Alexander Pritzel;Benigno Uria;Sriram Srinivasan;Adrià Puigdomènech Badia

  • Agent57: Outperforming the Atari Human Benchmark

    Adrià Puigdomènech Badia;Bilal Piot;Steven Kapturowski;Pablo Sprechmann

  • Model-Free Episodic Control

    Charles Blundell;Benigno Uria;Alexander Pritzel;Yazhe Li

  • Bayesian Recurrent Neural Networks

    Meire Fortunato;Charles Blundell;Oriol Vinyals

  • Computations Underlying Social Hierarchy Learning: Distinct Neural Mechanisms for Updating and Representing Self-Relevant Information.

    Dharshan Kumaran;Dharshan Kumaran;Andrea Banino;Charles Blundell;Demis Hassabis

  • Never Give Up: Learning Directed Exploration Strategies

    Adrià Puigdomènech Badia;Pablo Sprechmann;Alex Vitvitskyi;Daniel Guo

  • Representation Learning via Invariant Causal Mechanisms

    Jovana Mitrovic;Brian McWilliams;Jacob C Walker;Lars Holger Buesing

Frequent Co-Authors

Demis Hassabis
Demis Hassabis Google (United States)
Yee Whye Teh
Yee Whye Teh University of Oxford
Daan Wierstra
Daan Wierstra DeepMind (United Kingdom)
Matthew Botvinick
Matthew Botvinick Yale University
Razvan Pascanu
Razvan Pascanu DeepMind (United Kingdom)
Oriol Vinyals
Oriol Vinyals DeepMind (United Kingdom)
Dharshan Kumaran
Dharshan Kumaran Google (United States)
Katherine A. Heller
Katherine A. Heller Google (United States)
Koray Kavukcuoglu
Koray Kavukcuoglu DeepMind (United Kingdom)
Michael C. Mozer
Michael C. Mozer Google (United States)

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

Considering a Computer Science degree? The field offers many online alternatives that can broaden your skill set and career options. For those interested in fundamental sciences, a bachelor of science in physics online provides analytical and problem-solving foundations valuable in tech careers.

Data-driven roles are in high demand, making the cheapest data science masters in usa a smart investment for career changers or upskillers. Electrical engineering is another core discipline driving innovation. An online master’s in electrical engineering degree can complement computer science skills in areas like embedded systems and hardware design.

If you prefer a quicker path to employment or want to boost your qualifications, consider certificate programs that pay well. These programs can provide job-ready skills without years of study.

By exploring these related online degrees and career pathways, you can tailor your learning to fit your ambitions and the changing needs of the tech industry.

Best Scientists Citing Charles Blundell

Trending Scientists

Recently Published Articles