IBM Redbooks

Jana Jamsek

Jim Cook

Dan Johansson

Kohichiroh Nishiue

This IBM Redbooks publication provides a getting started level of information about supporting the IBM Virtualization Engine TS7510 under i5/OS, primarily using the Backup Recovery and Media Services (BRMS), 5722-BR1, management product. BRMS is the primary backup and recovery management product for i5/OS. This book cannot make you an expert in i5/OS backup and recovery or in the use of BRMS. It also cannot make you an expert in full usage and management of the IBM Virtualization Engine TS7510 capabilities. More complete coverage of the TS7510 is included in the book IBM Virtualization Engine TS7510: Tape Virtualization for Open Systems Servers, SG24-7189. However, this book does provide sufficient information and examples to get you up and running with the IBM Virtualization Engine TS7510 attached to an i5/OS partition or system using BRMS. This book also helps you to understand where the IBM Virtualization Engine TS7510 can fit into your complete set of backup and recovery processes where multiple systems or servers, or logical partitions have to save data to a common repository. The TS7510 helps you to minimize your backup window, facilitates data sharing among the multiple systems, and helps you to minimize your total cost of ownership (TCO) in the backup and recovery area.

The IBM Virtualization Engine TS7510: Getting Started with i5/OS and Backup Recovery and Media Services

Magnus Henrekson

The formalism of probabilistic graphical models provides a unifying framework for capturing complex dependencies among random variables, and building large-scale multivariate statistical models. Graphical models have become a focus of research in many statistical, computational and mathematical fields, including bioinformatics, communication theory, statistical physics, combinatorial optimization, signal and image processing, information retrieval and statistical machine learning. Many problems that arise in specific instances-including the key problems of computing marginals and modes of probability distributions-are best studied in the general setting. Working with exponential family representations, and exploiting the conjugate duality between the cumulant function and the entropy for exponential families, Graphical Models, Exponential Families and Variational Inference develops general variational representations of the problems of computing likelihoods, marginal probabilities and most probable configurations. It describes how a wide variety of algorithms- among them sum-product, cluster variational methods, expectation-propagation, mean field methods, and max-product-can all be understood in terms of exact or approximate forms of these variational representations. The variational approach provides a complementary alternative to Markov chain Monte Carlo as a general source of approximation methods for inference in large-scale statistical models.

Dan Johansson

About

Books

Join the club