000			01759nam a2200253 4500
005			20251017160406.0
008			241213b |||||||| |||| 00| 0 eng d
020			_a9781107163447
041			_aeng
082			_a006.31 _bHenP
100			_aHennig, Philipp
245			_aProbabilistic Numerics : _bComputation as Machine Learning / _cPhilipp Hennig, Michael A. Osborne and Hans P. Kersting
260			_aCambridge: _bCambridge University Press; _c©2022
300			_axii, 410p.
520			_aProbabilistic 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.
650			_aComputer science, information & general works
650			_aComputer science, knowledge & systems
650			_aSpecial computer methods
650			_aArtificial Intelligence
650			_aMachine Learning
700			_aOsborne, Michael A.
700			_aKersting, Hans P.
942			_cBK
999			_c7202 _d7202