Peter Dayan is the director of the Gatsby Computational Neuroscience Unit at University College London. He is co-author of Theoretical Neuroscience, a textbook in computational and mathematical modeling of brain function. He is known for applying Bayesian methods from machine learning and artificial intelligence to understand neural function, and is particularly recognized for having related neurotransmitter levels to prediction errors and Bayesian uncertainties. He co-authored Q-learning with Chris Watkins, and provided a proof of convergence of TD(λ) for arbitrary λ.[clarification needed] His h-index according to Google Scholar is 76.
He began his career studying mathematics at the University of Cambridge (UK) and then continued for a PhD in artificial intelligence at the University of Edinburgh on the topic of 'Reinforcing connectionism: learning the statistical way' with David Willshaw, focusing on associative memory and reinforcement learning. He then went on to do a postdoc with Terry Sejnowski at the Salk Institute. He then took up an assistant professor position at the Massachusetts Institute of Technology, and later moved to University College London, where he became Professor and Director of the Gatsby Computational Neuroscience Unit.
- Schultz, W., Dayan, P., & Montague, P. R. (1997). A neural substrate of prediction and reward. Science, 275(5306), 1593–1599.
- Dayan, Peter. "The convergence of TD (λ) for general λ". Machine learning 8, no. 3–4 (1992): 341–362.
- Watkins, Christopher JCH, and Peter Dayan. "Q-learning". Machine learning 8, no. 3–4 (1992): 279–292.
- Samuel, Dayan, Peter (1991). "Reinforcing connectionism: learning the statistical way".
- David Willshaw