Advanced mean field methods : theory and practice / edited by Manfred Opper and David Saad.
Τύπος υλικού:
ΚείμενοΣειρά: Neural information processing seriesΛεπτομέρειες δημοσίευσης: Cambridge, Mass. : MIT Press, c2001.Περιγραφή: 1 ηλεκτρονική πηγή (xiii, 273 σ.) : εικISBN: - 0585417725
- 9780585417721
- 0262281058
- 9780262281058
- 0262150549
- 9780262150545
- 530.15/95 21
Includes bibliographical references.
1. Introduction / Manfred Opper and David Saad -- 2. From Naive Mean Field Theory to the TAP Equations / Manfred Opper and Ole Winther -- 3. An Idiosyncratic Journey Beyond Mean Field Theory / Jonathan S. Yedidia -- 4. Mean Field Theory for Graphical Models / Hilbert J. Kappen and Wim J. Wiegerinck -- 5. The TAP Approach to Intensive and Extensive Connectivity Systems / Yoshiyuki Kabashima and David Saad -- 6. TAP For Parity Check Error Correcting Codes / David Saad, Yoshiyuki Kabashima and Renato Vicente -- 7. Adaptive TAP Equations / Manfred Opper and Ole Winther -- 8. Mean-field Theory of Learning: From Dynamics to Statics / K.Y. Michael Wong, S. Li and Peixun Luo.
"Bringing together ideas and techniques from diverse disciplines, this book covers the theoretical foundations of advanced mean field methods, explores the relation between the different approaches, examines the quality of the approximation obtained, and demonstrates their application to various areas of probabilistic modeling."--Jacket.
