Murray Shanahan - Imperial College London (original) (raw)
Professor of Cognitive Robotics, Department of Computing, Imperial College London
Principal Research Scientist, Google DeepMind
Email: m.shanahan@imperial.ac.uk
Twitter: @mpshanahan
Biography
I am a principal research scientist at Google DeepMind and Professor of Cognitive Robotics at Imperial College London. Educated at Imperial College (BSc(Eng) computer science, 1984) and Cambridge University (King’s College; PhD computer science, 1988), I became a full professor at Imperial in 2006, and joined DeepMind in 2017. My publications span artificial intelligence, machine learning, logic, dynamical systems, computational neuroscience, and philosophy of mind. I am active in public engagement, and was scientific advisor on the film Ex Machina. I have written several books, including “Embodiment and the Inner Life” (2010) and “The Technological Singularity” (2015).
Research Overview
I have devoted my career to trying to understand cognition and consciousness in the space of possible minds. This space of possibilities encompasses biological brains, human and animal, as well as artificial intelligence. I like to look at the topic from multiple, interdisciplinary perspectives: computational, empirical, and philosophical. I worked in classical, symbolic AI for over 10 years, concentrating on so-called common sense reasoning. I then spent 10 years or so studying the biological brain, specifically how its connectivity and dynamics support cognition and consciousness. (I have been particularly influenced by global workspace theory.) Then, when AI got exciting again, I migrated to machine learning, where I got involved in deep reinforcement learning. Most recently, I have been working with large language models, trying to understand them from theoretical, philosophical, and practical points of view.
Selected Publications
This is a small selection of my published work, organised into themes, in roughly reverse chronological order. I've chosen publications either because they are highly cited or because they contain material I am somewhat attached to. For a more complete list see my Google Scholar page. For a slightly deeper dive into my work, along with some intellectual context and historical perspective, click on the relevant theme headings.
Deep Learning
- Abstraction for deep reinforcement learning
M. Shanahan, M. Mitchell
International Joint Conference on Artificial Intelligence, 5588-5596 (2022) - Artificial intelligence and the common sense of animals
M Shanahan, M Crosby, B Beyret, L Cheke
Trends in Cognitive Sciences, 24 (11), 862-872 (2020) - An explicitly relational neural network architecture
M Shanahan, K Nikiforou, A Creswell, C Kaplanis, D Barrett, M Garnelo
International Conference on Machine Learning, 8593-8603 (2020) - Reconciling deep learning with symbolic artificial intelligence: Representing objects and relations
M Garnelo, M Shanahan
Current Opinion in Behavioral Sciences, 29, 17-23 (2019) - Conditional neural processes
M. Garnelo, D. Rosenbaum, C. Maddison, T. Ramalho, D. Saxton, M Shanahan, YW Teh, D Rezende, SM Ali Eslami
International Conference on Machine Learning, 1704-1713 (2018) - Deep unsupervised clustering with Gaussian mixture variational autoencoders
N Dilokthanakul, PAM Mediano, M Garnelo, MCH Lee, H Salimbeni, K Arulkumaran, M Shanahan
arXiv preprint arXiv:1611.02648 (2016)
Brain Dynamics and Connectivity
- Integrated information as a common signature of dynamical and information-processing complexity
PAM Mediano, FE Rosas, JC Farah, M Shanahan, D Bor, AB Barrett
Chaos, 32 (2022) - The control of global brain dynamics: opposing actions of frontoparietal control and default mode networks on attention
PJ Hellyer, M Shanahan, G Scott, RJS Wise, DJ Sharp, R Leech
Journal of Neuroscience, 34, 451-461 (2014) - Large-scale network organization in the avian forebrain: A connectivity matrix and theoretical analysis
M Shanahan, VP Bingman, T Shimizu, M Wild, O Güntürkün
Frontiers in Computational Neuroscience, 7, 89 (2013) - The brain's connective core and its role in animal cognition
M Shanahan
Philosophical Transactions of the Royal Society B: Biological Sciences, 367, 2704-2714 (2012) - Metastable chimera states in community-structured oscillator networks
M Shanahan
Chaos, 20 (1) (2010)
Consciousness and Philosophy of Mind
- Conscious exotica
M. Shanahan
Aeon (October 2016) - Satori before singularity
M Shanahan
Journal of Consciousness Studies, 19 (7-8), 87-102 (2012) - Embodiment and the inner life: Cognition and consciousness in the space of possible minds
M Shanahan
Oxford University Press (2010) - A cognitive architecture that combines internal simulation with a global workspace
M Shanahan
Consciousness and Cognition, 15, 433-449 (2006) - Applying global workspace theory to the frame problem
M. Shanahan, B. Baars
Cognition, 98 (2), 157-176 (2005) - Global access, embodiment and the conscious subject
M Shanahan
Journal of Consciousness Studies, 12 (12), 46-66 (2005)
Symbolic AI
- Perception as abduction: Turning sensor data into meaningful representation
M. Shanahan
Cognitive Science, 29(1), 103-134 (2005) - An attempt to formalise a non-trivial benchmark problem in common sense reasoning
M Shanahan
Artificial Intelligence, 153(1-2), 141-165 (2004) - An abductive event calculus planner
M Shanahan
The Journal of Logic Programming, 44 (1-3), 207-240 (2000) - Robotics and the common sense informatic situation
M Shanahan
European Conference on Artificial Intelligence, 684-688 (1996) - Default reasoning about spatial occupancy
M Shanahan
Artificial Intelligence, 74, 147-163 (1995)