Probabilistic Numerics - Computation As Machine Learning

Probabilistic numerical computation formalises the connection between machine learning and applied mathematics. Numerical algorithms approximate intractable quantities from computable ones. They estimate integrals from evaluations of the integrand, or the path of a dynamical system described by differential equations from evaluations of the vector field. In other words, they infer a latent quantity from data. This book shows that it is thus formally possible to think of computational routines as learning machines, and to use the notion of Bayesian inference to build more flexible, efficient, or customised algorithms for computation. The text caters for Masters' and PhD students, as well as postgraduate researchers in artificial intelligence, computer science, statistics, and applied mathematics. Extensive background material is provided along with a wealth of figures, worked examples, and exercises (with solutions) to develop intuition.

Product details

• Authors: et al, Philipp Hennig, Philipp (Eberhard-Karls-Universitat Tubing Hennig, Philipp (Eberhard-Karls-Universitat Tubingen Hennig, Hans P. Kersting, Hans P. (Ecole Normale Superieure Kersting, Michael A. Osborne, Michael A. (University of Oxford) Osborne, Osborne Michael A.
• Publisher: Cambridge University Press Academic
• Languages: English
• Product format: Hardback
• Released: 31.08.2022
• EAN: 9781107163447
• ISBN: 978-1-107-16344-7
• No. of pages: 410
• Dimensions: 210 mm x 260 mm x 22 mm
• Subjects: Natural sciences, medicine, IT, technology > IT, data processing > IT; machine learning, MATHEMATICS / Probability & Statistics / General, COMPUTERS / Programming / Algorithms, MATHEMATICS / Numerical Analysis, COMPUTERS / Machine Theory, algorithms and data structures, Probability & statistics, Algorithms & data structures, Numerical analysis, Mathematical theory of computation, Probability and statistics, COMPUTERS / Data Science / Machine Learning