Abstract: There has been a very fruitful cross-fertilisation between AI and a variety of scientific disciplines. In this talk I will outline the main challenges, as well as opportunities such truly cross-disciplinary work opens up. In particular, we need a consistent mathematical framework in which to formulate learning in the space of scientific theories, as opposed to learning in the usual data spaces that take the form of finite-dimensional vector spaces, or graph data. A suggestion for such a theoretical framework will be provided, along with examples of its use in cognitive neuroscience, bio-medical sciences and astrophysics.
School of Computer Science, University of Birmingham, UK
Peter the Chair position in Complex and Adaptive Systems at the School of Computer Science, University of Birmingham, UK. His interests span machine learning, neural computation, probabilistic modelling and dynamical systems. Peter is fascinated by the possibilities of cross-disciplinary blending of machine learning, mathematical modelling and domain knowledge in a variety of scientific disciplines ranging from astrophysics to bio-medical sciences.
He has served on editorial boards of a variety of journals including IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Cybernetics, Scientific Reports, and Neural Computation and (co-)chaired Task Force on Mining Complex Astronomical Data and Neural Networks Technical Committee (TC of IEEE Computational Intelligence Society). Peter led an EPSRC-funded consortium of six UK universities on developing new mathematics for personalised healthcare. He was a recipient of the Fulbright Fellowship to work at NEC Research Institute, Princeton, USA, on dynamics of recurrent neural networks, UK-Hong-Kong Fellowship for Excellence, three Outstanding Paper of the Year Awards from the IEEE Transactions on Neural Networks and the IEEE Transactions on Evolutionary Computation, and the Best Paper Award at ICANN 2002.