Information Theory, Inference and Learning Algorithms Review

Average Reviews:

(More customer reviews)Uniting information theory and inference in an interactive and entertaining way, this book has been a constant source of inspiration, intuition and insight for me. It is packed full of stuff - its contents appear to grow the more I look - but the layering of the material means the abundance of topics does not confuse.
This is _not_ just a book for the experts. However, you will need to think and interact when reading it. That is, after all, how you learn, and the book helps and guides you in this with many puzzles and problems.

Click Here to see more reviews about: Information Theory, Inference and Learning Algorithms

Information theory and inference, often taught separately, are here united in one entertaining textbook. These topics lie at the heart of many exciting areas of contemporary science and engineering - communication, signal processing, data mining, machine learning, pattern recognition, computational neuroscience, bioinformatics, and cryptography.This textbook introduces theory in tandem with applications. Information theory is taught alongside practical communication systems, such as arithmetic coding for data compression and sparse-graph codes for error-correction. A toolbox of inference techniques, including message-passing algorithms, Monte Carlo methods, and variational approximations, are developed alongside applications of these tools to clustering, convolutional codes, independent component analysis, and neural networks.The final part of the book describes the state of the art in error-correcting codes, including low-density parity-check codes, turbo codes, and digital fountain codes -- the twenty-first century standards for satellite communications, disk drives, and data broadcast. Richly illustrated, filled with worked examples and over 400 exercises, some with detailed solutions, David MacKay's groundbreaking book is ideal for self-learning and for undergraduate or graduate courses. Interludes on crosswords, evolution, and sex provide entertainment along the way.In sum, this is a textbook on information, communication, and coding for a new generation of students, and an unparalleled entry point into these subjects for professionals in areas as diverse as computational biology, financial engineering, and machine learning.

Get 21% OFF

Click here for more information about Information Theory, Inference and Learning Algorithms

Read More...

Learning in Graphical Models (Adaptive Computation and Machine Learning) Review

Average Reviews:

(More customer reviews)The title of the book is somewhat misleading, in that most of the research papers involve advanced issues concerning one particular graphical model, namely the Bayesian network. For this reason I highly recommend, as a prerequisite to this book, Finn Jensen's "Bayesian Networks and Decision Graphs". Jensen's book is adequate in giving a good introduction and overview of the subject, but not sufficient for calling oneself an "expert" upon successfully digesting it.
To its credit, "Learning in Graphical Models" has several well-written and interesting papers, but the tutorial papers just did not seem enough of an introduction for me to feel comfortable using it as a first source of introduction.
What I find most compelling about Bayesian networks is the fact that they seem both highly modular (which facilitates reusability and network interconnectivity) and can be designed in a semi-rational manner (contrast this with neural-network architectures for which few good algorithms exist for determining size and number of layers). For this reason I imagine they will be important players in future engineering projects that require learning and adaptation.

Click Here to see more reviews about: Learning in Graphical Models (Adaptive Computation and Machine Learning)

Graphical models, a marriage between probability theory and graph theory,provide a natural tool for dealing with two problems that occur throughout appliedmathematics and engineering--uncertainty and complexity. In particular, they play anincreasingly important role in the design and analysis of machine learningalgorithms. Fundamental to the idea of a graphical model is the notion ofmodularity: a complex system is built by combining simpler parts. Probability theoryserves as the glue whereby the parts are combined, ensuring that the system as awhole is consistent and providing ways to interface models to data. Graph theoryprovides both an intuitively appealing interface by which humans can model highlyinteracting sets of variables and a data structure that lends itself naturally tothe design of efficient general-purpose algorithms.This book presents an in-depthexploration of issues related to learning within the graphical model formalism. Fourchapters are tutorial chapters--Robert Cowell on Inference for Bayesian Networks,David MacKay on Monte Carlo Methods, Michael I. Jordan et al. on VariationalMethods, and David Heckerman on Learning with Bayesian Networks. The remainingchapters cover a wide range of topics of current research interest.

Get 20% OFF

Click here for more information about Learning in Graphical Models (Adaptive Computation and Machine Learning)

Read More...

Utility-Based Learning from Data (Chapman & Hall/CRC Machine Learning & Pattern Recognition) Review

Average Reviews:

(More customer reviews)This book is just as great inside the cover as
the elegant cover leads you to expect.
A very ambitious book with a very broad scope.
As a Professor of Applied Mathematics and
of mathematical finance, I very much look
forward to presenting parts of this material
in the future.
Concerning the contents, citing from the introduction of
the book:"Our point of view is motivated by the notion that probabilistic models are
usually not learned for their own sake-rather, they are used to make decisions"
and "finance and decision theory provide a language in which it is
natural to express these assumptions-namely, utility theory-and formulate,
from first principals, model performance measures and the notion of optimal
and robust model performance"
and the books purpose is : " to provide a pedagogical and self-contained discussion of a select set of
methods for estimating probability distributions that can be approached
coherently from a decision-theoretic point of view"
The last sentence is extremely telling. Friedman and Sandow indeed
demonstrate in this book that, in struggling to quantify
default risk, in their daytime jobs at Standard and Poor's,
they carefully put into place their own approach, and painstakingly
tested it on read data, throughout many different economic
cycles (as far back as 2001, when I worked in Friedman's group).
In addition, after Friedman presented some of this material at
New York University's Courant Institute, Friedman and Sandow saw fit to
include a through introduction to topics which are of interest
to all economic students, such as utility theory and
minimum relative theory. And they do so in a crisp, clear and no-nonsense
manner that is rarely seen in books on economics.
A key aspect of the point of view taken in this book, is to relate
betting odds, such as in a horse race, to expected
growth of wealth.
Readers should race to the bookstore to get a
hold of this book!

Click Here to see more reviews about: Utility-Based Learning from Data (Chapman & Hall/CRC Machine Learning & Pattern Recognition)

Utility-Based Learning from Data provides a pedagogical, self-contained discussion of probability estimation methods via a coherent approach from the viewpoint of a decision maker who acts in an uncertain environment. This approach is motivated by the idea that probabilistic models are usually not learned for their own sake; rather, they are used to make decisions. Specifically, the authors adopt the point of view of a decision maker who(i) operates in an uncertain environment where the consequences of possible outcomes are explicitly monetized,(ii) bases his decisions on a probabilistic model, and(iii) builds and assesses his models accordingly.These assumptions are naturally expressed in the language of utility theory, which is well known from finance and decision theory. By taking this point of view, the book sheds light on and generalizes some popular statistical learning approaches, connecting ideas from information theory, statistics, and finance. It strikes a balance between rigor and intuition, conveying the main ideas to as wide an audience as possible.

Get 19% OFF

Click here for more information about Utility-Based Learning from Data (Chapman & Hall/CRC Machine Learning & Pattern Recognition)

Read More...

Handbook of Mathematical Models in Computer Vision Review

Average Reviews:

(More customer reviews)When attending a general computer vision conference like xCCV, did you ever feel lost at certain sessions? Well, don't always blame the presenters! The field covered by Computer Vision has become so broad that it is almost impossible to understand what is going on and to keep track of the latest developments. To (partially) overcome this problem, the editors of the Handbook of Mathematical Models in Computer Vision have done a great job.
One can become a bit skeptical reading such a title. How complete can such a handbook be? However, going through the 33 chapters, indeed a wide breadth is treated. The focus of the book is on mathematical methods that both model and reproduce human visual abilities. This is the field of biological vision in which the editors have a strong background.
The editors chose three distinct categories of mathematical models, namely variational techniques (those attending Prof. Faugeras' talk at ICPR 2006 may remember his statement that they give the fundamental equations in computer vision!), statistical methods, and combinatorial approaches. The chapters are grouped in six sections that circle around these three categories. Although going through the book chapters by mentioning keyword may yield a rather boring list, it shows the wide variety of topics that are being dealt with.
The book starts with a section on low-level vision: Image Reconstruction. Here one can find information on diffusion filters and wavelets, total variation methods, and PDE based inpainting.
The second section is concerned with Boundary Extraction, Segmentation and Grouping. Here subjects like levelings, graph cuts, minimal paths and fast marching methods, deformable models, variational segmentation with shape priors, curve propagation, level set methods, and a stochastic model of geometric snakes are discussed.
Section three switches to high level vision. It deals with Shape Modeling & Registration, divided into topics concerning invariant processing and occlusion resistant recognition, image-based inferences, point matching and uncertainty-driven, point-based image registration.
In the fourth section, Motion Analysis, Optical Flow & Tracking, the concept of time is added and one encounters the topics of optical flow estimation, image warping, alignment and stitching, visual tracking, image and video segmentation, human motion capture, and dynamic textures.
Section five deals with 3D from Images, Projective Geometry & Stereo Reconstruction, treated by boundary detection, stereo, texture and color, shape from shading, calibration, motion and shape recovery, multi-view reconstruction, binocular stereo with occlusions, and modeling non-rigid dynamic scenes.
The last section may seem a bit odd: Applications: Medical Image Analysis. However, this is one of the most prominent areas in computer vision. Although here certain vision aspects do not occur, compared to natural images (just think of the influence of the sun), for many tasks the performance of the mathematical methods can be evaluated since a ground truth is often available - provided by humans whom the models are supposed to mimic. In this section, applications of interactive graph-based segmentation methods, 3D active shape and appearance models, characterization of diffusion anisotropy, segmentation, variational approaches, and statistical methods of registration are given.
The danger of publishing an edited volume is the difference in style and treatment of the topics among the various contributions. This is not the case here. Each chapter gives a general introduction to the topic, introduces the mathematical model, discusses the underlying ideas globally, and shows some results. For the full details the readers are referred to the extensive bibliography with 929 entries.
This book is a must-have for those interested in the full breadth of research done in the biological & computer vision community. As a bonus, the chapters can also be used in a seminar-based, advanced undergraduate course in mathematical based computer vision.


Click Here to see more reviews about: Handbook of Mathematical Models in Computer Vision

This comprehensive volume is an essential reference tool for professional and academic researchers in the filed of computer vision, image processing, and applied mathematics. Continuing rapid advances in image processing have been enhanced by the theoretical efforts of mathematicians and engineers. This marriage of mathematics and computer vision - computational vision - has resulted in a discrete approach to image processing that is more reliable when leveraging in practical tasks. This comprehensive volume provides a detailed discourse on the mathematical models used in computational vision from leading educators and active research experts in this field. Topical areas include: image reconstruction, segmentation and object extraction, shape modeling and registration, motion analysis and tracking, and 3D from images, geometry and reconstruction. The book also includes a study of applications in medical image analysis.Handbook of Mathematical Models in Computer Vision provides a graduate-level treatment of this subject as well as serving as a complete reference work for professionals.

Get 21% OFF

Click here for more information about Handbook of Mathematical Models in Computer Vision

Read More...

Temporal Data Mining (Chapman & Hall/CRC Data Mining and Knowledge Discovery Series) Review

Average Reviews:

(More customer reviews)A survey of remarkable breadth, listing hundreds of sources: 50-100 items per chapter, majority of them from conference proceedings. Evidently, this kind of volume does not let the author discuss any particular paper or topic in detail; at best, a reference is covered with a short paragraph. This does create a problem: the book's value is exhausted once the reader looks up the topic of interest, and moves on to the suggested references. "Temporal data mining" could do with a little more editing, but I am quite impressed with it the way it is, an authoritative and wide-ranging introduction to an interesting topic.

Click Here to see more reviews about: Temporal Data Mining (Chapman & Hall/CRC Data Mining and Knowledge Discovery Series)

Temporal data mining deals with the harvesting of useful information from temporal data. New initiatives in health care and business organizations have increased the importance of temporal information in data today.From basic data mining concepts to state-of-the-art advances, Temporal Data Mining covers the theory of this subject as well as its application in a variety of fields. It discusses the incorporation of temporality in databases as well as temporal data representation, similarity computation, data classification, clustering, pattern discovery, and prediction. The book also explores the use of temporal data mining in medicine and biomedical informatics, business and industrial applications, web usage mining, and spatiotemporal data mining.Along with various state-of-the-art algorithms, each chapter includes detailed references and short descriptions of relevant algorithms and techniques described in other references. In the appendices, the author explains how data mining fits the overall goal of an organization and how these data can be interpreted for the purpose of characterizing a population. She also provides programs written in the Java language that implement some of the algorithms presented in the first chapter. Check out the author's blog at http://theophanomitsa.wordpress.com/

Get 29% OFF

Click here for more information about Temporal Data Mining (Chapman & Hall/CRC Data Mining and Knowledge Discovery Series)

Read More...

Probabilistic Graphical Models: Principles and Techniques (Adaptive Computation and Machine Learning series) Review

Average Reviews:

(More customer reviews)Stanford professor, Daphne Koller, and her co-author, Professor Nir Friedman, employed graphical models to motivate thoroughgoing explorations of representation, inference and learning in both Bayesian networks and Markov networks. They do their own bidding at the book's web page, [...], by giving readers a panoramic view of the book in an introductory chapter and a Table of Contents. On the same page, there is a link to an extensive Errata file which lists all the known errors and corrections made in subsequent printings of the book - all the corrections had been incorporated into the copy I have. The authors painstakingly provided necessary background materials from both probability theory and graph theory in the second chapter. Furthermore, in an Appendix, more tutorials are offered on information theory, algorithms and combinatorial optimization. This book is an authoritative extension of Professor Judea Pearl's seminal work on developing the Bayesian Networks framework for causal reasoning and decision making under uncertainty. Before this book was published, I sent an e-mail to Professor Koller requesting some clarification of her paper on object-oriented Bayesian networks; she was most generous in writing an elaborate reply with deliberate speed.

Click Here to see more reviews about: Probabilistic Graphical Models: Principles and Techniques (Adaptive Computation and Machine Learning series)

A general framework for constructing and using probabilistic models ofcomplex systems that would enable a computer to use available information for makingdecisions.

Get 21% OFF

Click here for more information about Probabilistic Graphical Models: Principles and Techniques (Adaptive Computation and Machine Learning series)

Read More...

Linear and Nonlinear Programming (International Series in Operations Research & Management Science) Review

Average Reviews:

(More customer reviews)I have profitably used the book to apply constrained minimization procedures in the field of computational contact mechanics. I think it is not a secret that quite often books on mathematics are written from matematicians for matematicians. Hence it is quite hard for engineers both to read and to extract valuable information from them. With this respect this book is a shining star. It presents the topics in a very precise but clear and understandable way. Moreover the notation also is the best compromise between coinciseness and clarity. Matematicians, please, look at this book and follow such style; we engineer desperately need to communicate with you.

Click Here to see more reviews about: Linear and Nonlinear Programming (International Series in Operations Research & Management Science)

Get 20% OFF

Click here for more information about Linear and Nonlinear Programming (International Series in Operations Research & Management Science)

Read More...

Analogy-Making as Perception: A Computer Model (Neural Network Modeling and Connectionism) Review

Average Reviews:

(More customer reviews)Melanie Mitchell's analogy-making as perception is a remarkably original book. It documents an artificial intelligence project known as copycat, which was implemented as the author's PhD project under Douglas Hofstadter.
Copycat is unlike anything in artificial intelligence. It is not a symbolic system, neither a connectionist one. The major goal of the project is to study the nature of concepts. Concepts, as we all know, are flexible, context-sensitive creatures. For instance, DNA has nothing to do with a computer program, but there is a sense on which we can see DNA as a computer program that guides embrionary development. DNA can also be seen as a zipper, as it "zips down" in two parts (for cell reproduction). Still another view would be DNA as a will, for it carries valuable hereditary "property". Now, DNA is in truth just a molecule, and nothing else. The question is, how can we see the same thing (such as DNA) as so many different things? Moreover, how can these fluid context-sensitive concepts be implemented in rigid, rule-obeying computers?
To which the answer is: what we view is the abstract roles that DNA plays in embrionary development, cell division, and in individual reproduction. And this is the very idea of "Analogy-making as perception".
Well, not so fast. The copycat project is not designed to grasp such extremely complex subjects as DNA, but, on the other hand, it presents a computational architecture that suggests what the nature of concepts is like, and how flexible concepts may emerge from inflexible mechanisms.
Copycat can solve analogy problems such as abc->abd:ijk-> ?. But it is not restricted to trivial ones. Consider the following analogy: abc ->abd:xyz->?. How would you solve it? How do you think that copycat solves it?
Obviously, this project doesn't fit in very easily in classical artificial intelligence, as it attacks some of the most pervasive ideas of the field, such as the separation of perception and cognition. In fact, I think this book redefines the major questions of artificial intelligence (and although Mitchell does not state it, I think the copycat model does not fall prey to either the frame problem or to the symbol grounding problem).
It is very unfortunate that this is not one of the best-selling books in AI. But I believe that it will ultimately make its mark on the History of the field, if for no other reason than it simply is the right approach to genuine intelligence and authentic understanding.
Should one day Amazon.com let me give a 6-star to a book, but charge me a dollar for giving it, this is one that would definitely deserve to be such a 6-star.
============================================
PS. I would also recommend Hofstadter's Fluid Concepts and Creative Analogies; and Robert French's Subtlety of Sameness.

Click Here to see more reviews about: Analogy-Making as Perception: A Computer Model (Neural Network Modeling and Connectionism)

The psychologist William James observed that "a native talent forperceiving analogies is... the leading fact in genius of every order." Thecentrality and the ubiquity of analogy in creative thought have been noted again andagain by scientists, artists, and writers, and understanding and modeling analogicalthought have emerged as two of the most important challenges for cognitivescience.Analogy-Making as Perception is based on the premise that analogy-making isfundamentally a high-level perceptual process in which the interaction of perceptionand concepts gives rise to "conceptual slippages" which allow analogies to be made.It describes Copycat - a computer model of analogymaking, developed by the authorwith Douglas Hofstadter, that models the complex, subconscious interaction betweenperception and concepts that underlies the creation of analogies.In Copycat, bothconcepts and high-level perception are emergent phenomena, arising from largenumbers of low-level, parallel, non-deterministic activities. In the spectrum ofcognitive modeling approaches, Copycat occupies a unique intermediate positionbetween symbolic systems and connectionist systems a position that is at present themost useful one for understanding the fluidity of concepts and high-levelperception.On one level the work described here is about analogy-making, but onanother level it is about cognition in general. It explores such issues as thenature of concepts and perception and the emergence of highly flexible concepts froma lower-level "subcognitive" substrate.Melanie Mitchell, Assistant Professor in theDepartment of Electrical Engineering and Computer Science at the University ofMichigan, is a Fellow of the Michigan Society of Fellows. She is also Director ofthe Adaptive Computation Program at the Santa Fe Institute.

Click here for more information about Analogy-Making as Perception: A Computer Model (Neural Network Modeling and Connectionism)

Read More...

Tutorial on Neural Systems Modeling Review

Average Reviews:

(More customer reviews)We used this book for the upper-level undergraduate students in an interdisciplinary computational neuroscience course at a small liberal arts college. This is a fine, well-written book. One of the strengths of this book is that it starts with very basic programming in Matlab, so that the students without programming backgrounds can easily follow along. The programs in the book are well commented, and they progress slowly and logically in complexity. More advanced math topics are well separated out in Math Boxes. The examples of the neural systems are covered in enough (but not too much) details to be interesting and accessible to the readers. The book is definitely considerate of and sensitive to the wonderfully interdisciplinary nature of this field, so that the materials can be digested by people with different backgrounds. One can not contain all the topics in computational neuroscience in a single book, but this book does a great job of covering many important and interesting ideas/areas (Hebbian learning, Hopfield model, lateral inhibition, adaptation, supervised and unsupervised learning, etc.).
It works very well as an introductory textbook (or tutorial) of the field. The codes and the discussions are clear and simple (not intended as an advanced textbook), and to me, that's the strength and unique quality of this book.
By the way, most of the computer programs listed in the book work well with Octave (as well as Matlab).

Click Here to see more reviews about: Tutorial on Neural Systems Modeling

Neural systems models are elegant conceptual tools that provide satisfying insight into brain function. The goal of this new book is to make these tools accessible. It is written specifically for students in neuroscience, cognitive science, and related areas who want to learn about neural systems modeling but lack extensive background in mathematics and computer programming.The book opens with an introduction to computer programming. Each of twelve subsequent chapters presents a different modeling paradigm by describing its basic structure and showing how it can be applied in understanding brain function. The text guides the reader through short, simple computer programs printed in the book and available by download at the companion website that implement the paradigms and simulate real neural systems. Motivation for the simulations is provided in the form of a narrative that places specific aspects of neural system behavior in the context of more general brain function. The narrative integrates instruction for using the programs with description of neural system function, and readers can actively experience the fun and excitement of doing the simulations themselves. Designed as a hands-on tutorial for students, this book also serves instructors as both a teaching tool and a source of examples and exercises that provide convenient starting points for more in-depth exploration of topics of their own specific interest.The distinguishing pedagogical feature of this book is its computer programs, written in MATLAB, that help readers develop basic skill in the area of neural systems modeling. (All of the program files are available online via the book s companion website. Actual data on real neural systems is presented in the book for comparison with the results of the simulations. Also included are asides ( Math Boxes ) that present mathematical material that is relevant but not essential to running the programs. Exercises and references at the end of each chapter invite readers to explore each topic area on their own.

Get 13% OFF

Click here for more information about Tutorial on Neural Systems Modeling

Read More...