Demis Hassabis

Research interests

Publications

• Mastering Atari, Go, chess and shogi by planning with a learned model

  RePEc: Research Papers in Economics ·

• Accurate structure prediction of biomolecular interactions with AlphaFold 3

  Nature · 2024 · https://doi.org/10.1038/s41586-024-07487-w

• Accurate proteome-wide missense variant effect prediction with AlphaMissense

  Science · 2023 · 10.1126/science.adg7492

• AlphaFold Protein Structure Database in 2024: providing structure coverage for over 214 million protein sequences

  Nucleic Acids Research · 2023 · https://doi.org/10.1093/nar/gkad1011

• Tackling Climate Change with Machine Learning

  OPUS 4 (Zuse Institute Berlin) · 2022 · https://doi.org/10.1145/3485128

• Magnetic control of tokamak plasmas through deep reinforcement learning

  Nature · 2022 · 10.1038/s41586-021-04301-9

• Highly accurate protein structure prediction with AlphaFold

  Nature · 2021 · https://doi.org/10.1038/s41586-021-03819-2

• AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models

  Nucleic Acids Research · 2021 · https://doi.org/10.1093/nar/gkab1061

• Protein complex prediction with AlphaFold-Multimer

  bioRxiv (Cold Spring Harbor Laboratory) · 2021 · 10.1101/2021.10.04.463034

• Highly accurate protein structure prediction for the human proteome

  Nature · 2021 · 10.1038/s41586-021-03828-1

• Improved protein structure prediction using potentials from deep learning

  Nature · 2020 · 10.1038/s41586-019-1923-7

• International evaluation of an AI system for breast cancer screening

  Nature · 2020 · 10.1038/s41586-019-1799-6

• A clinically applicable approach to continuous prediction of future acute kidney injury

  Nature · 2019 · 10.1038/s41586-019-1390-1

• Grandmaster level in StarCraft II using multi-agent reinforcement learning

  Nature · 2019 · 10.1038/s41586-019-1724-z

• Clinically applicable deep learning for diagnosis and referral in retinal disease

  Nature Medicine · 2018 · 10.1038/s41591-018-0107-6

• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

  Science · 2018 · 10.1126/science.aar6404

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

  arXiv (Cornell University) · 2017 · 10.48550/arxiv.1712.01815

• Neuroscience-Inspired Artificial Intelligence

  Neuron · 2017 · 10.1016/j.neuron.2017.06.011

• Overcoming catastrophic forgetting in neural networks

  Proceedings of the National Academy of Sciences · 2017 · 10.1073/pnas.1611835114

• Mastering the game of Go without human knowledge

  Nature · 2017 · https://doi.org/10.1038/nature24270

• Hybrid computing using a neural network with dynamic external memory

  Nature · 2016 · 10.1038/nature20101

• Mastering the game of Go with deep neural networks and tree search

  Nature · 2016 · https://doi.org/10.1038/nature16961

• Human-level control through deep reinforcement learning

  Nature · 2015 · https://doi.org/10.1038/nature14236

• The Future of Memory: Remembering, Imagining, and the Brain

  Neuron · 2012 · 10.1016/j.neuron.2012.11.001

• Patients with hippocampal amnesia cannot imagine new experiences

  Proceedings of the National Academy of Sciences · 2007 · 10.1073/pnas.0610561104

• When Fear Is Near: Threat Imminence Elicits Prefrontal-Periaqueductal Gray Shifts in Humans

  Science · 2007 · 10.1126/science.1144298

• Deconstructing episodic memory with construction

  Trends in Cognitive Sciences · 2007 · 10.1016/j.tics.2007.05.001

Current projects

No projects listed.