Machine learning : a Bayesian and optimization perspective /
Sergios Theodoridis
- Second edition
- xxvii, [1], 1131 pagesa : illustrations
Includes bibliography
Probability and stochastic processes -- Learning in parametric modeling: basic concepts and directions -- Mean-square error linear estimation -- Stochastic gradient descent: the LMS algorithm -- The least-squares family -- Classification: a tour of the classics -- Parameter learning: a convex analytic path -- Sparsity-aware learning: concepts and theoretical foundations -- Sparcity-aware learning: algorithms and applications -- Learning in reproducing Kernel Hilbert spaces -- Bayesian learning: inference and the EM alogrithm -- Bayesian learning: approximate inference and nonparametric models -- Monte Carlo methods -- Probabilistic graphical models: Part I -- Probabilistic graphical models: Part II -- Particle filtering -- Neural networks and deep learning -- Dimensionality reduction -- Appendix A LInear algebra -- Appendix B Probability theory and statistics -- Appendix C Hints on constrained optimization.
"This tutorial text gives a unifying perspective on machine learning by covering both probabilistic and deterministic approaches--which are based on optimization techniques--together with the Bayesian inference approach, whose essence lies in the use of a hierarchy of probabilistic models"--Publisher's website.