Self-Organizing Maps

Book Description

The Self-Organizing Map (SOM), with its variants, is the most popular artificial neural network algorithm in the unsupervised learning category. Many fields of science have adopted the SOM as a standard analytical tool: in statistics,signal processing, control theory, financial analyses, experimental physics, chemistry and medicine. A new area is organization of very large document collections. The SOM is also one of the most realistic models of the biological brain functions.
This new edition includes a survey of over 2000 contemporary studies to cover the newest results; the case examples were provided with detailed formulae, illustrations and tables; a new chapter on software tools for SOM was written, other chapters were extended or reorganized.

Customer Reviews:

I love this book........2000-03-11

This is a wonderfully written, and excellent book. It assumes only minimal background knowledge but imparts a great deal of insight. I love the way that the author describes this area and the connections with deep and beautiful mathematics.

A very nice 'handbook' of sorts for users of SOMs........1999-08-05

The material is presented clearly and comprehensively from the unique perspective of the SOM originator himself. The inclusion of exhaustive references is particularly useful for the prospective researcher, but, at the risk of sounding ungrateful, I'm curious as to why paper titles were not included in the citations? Overall though, a very good reference.

Information Theory, Inference & Learning Algorithms

Average customer rating:

Outstanding book, especially for statisticians
Great wish it had more n option inverse problems
Great Book As Far As It Goes
A must have...
Good value text on a spread of interesting and useful topics

Information Theory, Inference & Learning Algorithms
David J. C. MacKay
Manufacturer: Cambridge University Press
ProductGroup: Book
Binding: Hardcover

General | Programming | Computers & Internet | Subjects | Books

Information Theory | Computer Science | Computers & Internet | Subjects | Books

Modeling & Simulation | Computer Science | Computers & Internet | Subjects | Books

General | Computers & Internet | Subjects | Books

General | Software | Computers & Internet | Subjects | Books

General | Physics | Science | Subjects | Books

All Deals | Blowout Books | Stores | Books

Computers & Internet | Blowout Books | Stores | Books

Science | Blowout Books | Stores | Books

All Titles | Qualifying Textbooks - Fall 2007 | Stores | Books

Computers & Internet | Qualifying Textbooks - Fall 2007 | Stores | Books

Professional | Qualifying Textbooks - Fall 2007 | Stores | Books

Science | Qualifying Textbooks - Fall 2007 | Stores | Books
Similar Items:

ASIN: 0521642981

Book Description

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.

Customer Reviews:

Outstanding book, especially for statisticians.......2007-10-02

I find it interesting that most of the people reviewing this book seem to be reviewing it as they would any other information theory textbook. Such a review, whether positive or critical, could not hope to give a complete picture of what this text actually is. There are many books on information theory, but what makes this book unique (and in my opinion what makes it so outstanding) is the way it integrates information theory with statistical inference. The book covers topics including coding theory, Bayesian inference, and neural networks, but it treats them all as different pieces of a unified puzzle, focusing more on the connections between these areas, and the philosophical implications of these connections, and less on delving into depth in one area or another.

This is a learning text, clearly meant to be read and understood. The presentation of topics is greatly expanded and includes much discussion, and although the book is dense, it is rarely concise. The exercises are absolutely essential to understanding the text. Although the author has made some effort to make certain chapters or topics independent, I think that this is one book for which it is best to more or less work straight through. For this reason and others, this book does not make a very good reference: occasionally nonstandard notation or terminology is used.

The biggest strength of this text, in my opinion, is on a philosophical level. It is my opinion, and in my opinion it is a great shame, that the vast majority of statistical theory and practice is highly arbitrary. This book will provide some tools to (at least in some cases) anchor your thinking to something less arbitrary. It's ironic that much of this is done within the Bayesian paradigm, something often viewed (and criticized) as being more arbitrary, not less so. But MacKay's way of thinking is highly compelling. This is a book that will not just teach you subjects and techniques, but will shape the way you think. It is one of the rare books that is able to teach how, why, and when certain techniques are applicable. It prepares one to "think outside the box".

I would recommend this book to anyone studying any of the topics covered by this book, including information theory, coding theory, statistical inference, or neural networks. This book is especially indispensable to a statistician, as there is no other book that I have found that covers information theory with an eye towards its application in statistical inference so well. This book is outstanding for self-study; it would also make a good textbook for a course, provided the course followed the development of the textbook very closely.

Great wish it had more n option inverse problems.......2007-07-16

This is fantastic book. Really takes an intuitive approach to the material. The explanation of occam's razor is worth the price of the whole book. Highly recommended.

Great Book As Far As It Goes.......2006-03-27

I have used this to get a good background in the topics covered, especially inference theory, and in general I found it to be great book which fills a market gap. The only sins I see are sins of omission. I personally would have enjoyed seeing a more task driven organization. I seem to need these methods periodically but I never seem to need the same method twice. Also, many of the techniques are heavily iterative, i.e., monte carlo, neural networks, etc. This is fine but much of what I do is in the context of simulations where 100,000 step iterative methods don't work so well because of resource constraints. Historically, that has been the problem with many of these methods. They are useful for relatively small domains but don't necessarily work that well for "real" problems. That is probably why more task oriented books are not available. Of course the author is following the outline of the current research into the subject manner which in turn is largely determined by "interesting" and "doable" problems. The real progess in this field will come when the problems are formulated more by what is needed in the nontraditional domains of application. A good example of a useful compression (and identification in some cases) technique that is not covered is Principal Component Analysis. Technically, it is in none of the technique domains covered in this book, but it would have been nice to see some of the methods in the book compared with PCA. The author does make the statement at one point that image recognition is an interesting problem for which the method being discussed at the time is used. Nevertheless, this is a great overview of the subject manner and is very entertaining. That in the long run probably explains the problem: it is a textbook.

A must have..........2005-03-01

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.

Good value text on a spread of interesting and useful topics.......2005-02-20

I am a PhD student in computer science. Over the last year and a half this book has been invaluable (and parts of it a fun diversion).

For a course I help teach, the intoductions to probability theory and information theory save a lot of work. They are accessible to students with a variety of backgrounds (they understand them and can read them online). They also lead directly into interesting problems.

While I am not directly studying data compression or error correcting codes, I found these sections compelling. Incredibly clear exposition; exciting challenges. How can we ever be certain of our data after bouncing it across the world and storing it on error-prone media (things I do every day)? How can we do it without >60 hard-disks sitting in our computer? The mathematics uses very clear notation --- functions are sketched when introduced, theorems are presented alongside pictures and explanations of what's really going on.

I should note that a small number (roughly 4 or 5 out of 50) of the chapters on advanced topics are much more terse than the majority of the book. They might not be of interest to all readers, but if they are, they are probably more friendly than finding a journal paper on the same topic.

Most importantly for me, the book is a valuable reference for Bayesian methods, on which MacKay is an authority. Sections IV and V brought me up to speed with several advanced topics I need for my research.

Average customer rating:

An excellent overview
Enjoying this book enormously

Learning Bayesian Networks
Richard E. Neapolitan
Manufacturer: Prentice Hall
ProductGroup: Book
Binding: Hardcover

General | Certification Central | Computers & Internet | Subjects | Books

General | Computers & Internet | Subjects | Books

All Titles | Qualifying Textbooks - Fall 2007 | Stores | Books

Computers & Internet | Qualifying Textbooks - Fall 2007 | Stores | Books
Similar Items:

ASIN: 0130125342

Customer Reviews:

An excellent overview.......2004-05-17

In just a decade, Bayesian networks have went from being a mere academic curiosity to a highly useful field with myriads of applications. Indeed, the applications of Bayesian networks are wide-ranging and include disparate fields such as network engineering, bioinformatics, medical diagnostics, and intelligent troubleshooting. This book gives a fine overview of the subject, and after reading it one will have an in-depth understanding of both the underlying foundations and the algorithms involved in using Bayesian networks. The reader will have to look elsewhere for applications of Bayesian networks, since they are only discussed briefly in the book. Due to space constraints, only the first four chapters will be reviewed here.

The author defines a Bayesian network as a graphical structure for representing the probabilistic relationship among a large number of variables and for performing probabilistic inference with these variables. Before the advent of Bayesian networks, probabilistic inference depended on the use of Bayes' theorem, which entailed that the problems examined be relatively simple, due to the exponential space and time complexity that can arise in the application of this theorem.

After a short review of probability theory in chapter 1, a discussion of the "philosophical" foundations of probability, and a discussion of the difficulties inherent in representing large instances and in performing inference over a large number of variables, the author introduces Bayesian networks as directed acyclic graphs satisfying the Markov condition. A brief discussion of NasoNet, which is a large-scale Bayesian network used in the diagnosis and prognosis of nasopharyngeal cancer, is given. The author then shows in detail how to create Bayesian networks using causal edges, introducing in the process the notion of manipulating variables and the notion of a causation between two variables. An interesting example of manipulation is given in the context of pharmaceuticals, and an example of bad manipulation is given.

Chapter 2 addresses the nature of dependencies in DAGs via the concept of `faithfulness' and entailed conditional independencies. Very important in this chapter is the notion of `d-separation', which identifies all and only those conditional independencies entailed by the Markov condition for G. An explicit algorithm is given for finding d-separations. D-separation is used to define a notion of Markov equivalence between DAGs containing the same set of nodes. Also discussed is the minimality condition, wherein a DAG will not satisfy the Markov condition with respect to a probability distribution if an edge is removed from it. The author shows every probability distribution satisfies the minimality condition with some DAG. The notion of a `Markov blanket' is introduced, which measures the extent to which the instantiation of a set of nodes close to a particular node can shield the node from the effect of all other nodes. A Markov boundary of a random variable is then defined as a Markov blanket such that none of its proper subsets is a Markov blanket of the random variable. The utility of these concepts lies in the fact that the set of all parents of each variable X, children of X, and parents of children of X are the unique Markov boundary of X, if the DAG satisfies the faithfulness condition.

Inference in Bayesian networks is the topic of chapter 3, with Pearl's message-passing algorithm starting off the discussion for the case of discrete random variables. This algorithm, which applies for Bayesian networks whose DAGs are trees, is based on a theorem, whose statement takes well over a page, and whose proof covers five pages. The author gives detailed examples though, and these are very helpful in understanding the algorithm. The Pearl algorithm is then generalized to singly and multiply connected networks. After a discussion of the computational complexity of the algorithm, the author then overviews the `noisy OR-gate model', which is a model whose complexity is manageable, since each variable in the model has only two values. The author then moves on to doing inference using an approach, called `symbolic probabilistic inference' that approximates finding the optimal way to compute marginal distributions of interest from the joint probability distribution. This algorithm involves a number of multiplications in order to compute the marginal probability. To minimize the computational effort, it would be advantageous to minimize the number of these multiplications, and so the author discusses the `optimal factoring problem', which, once solved for a given factoring instance, will give a factorization that requires a minimal number of multiplications. What follows after this is a very interesting discussion of the relationship of human reasoning to Bayesian networks. This is done via the introduction of the `causal network model', and the author then, quite unexpectedly, overviews the research on the testing of human subjects so as to test the accuracy of the model. These testing studies included those that involve inference based on `discounting', which measures to what degree an individual becomes less confident in the cause when told that a different cause of the effect was present. Another discussed is one that involves larger networks in the context of traffic congestion. This is followed by a discussion of a study of causal reasoning in the context of the debugging of programs.

Inference algorithms are studied for the case of continuous variables in chapter four. After a review of the normal probability distribution, the author discusses an inference algorithm for the case of Gaussian Bayesian networks. An algorithm for doing inference with continuous variables for singly connected Bayesian networks is given, that allows the determination of expected value and variance of each node conditioned on specified values of nodes in some subset. This is followed by several detailed and helpful examples of inference in continuous variables. As expected, issues with computational complexity arise, and so the author discusses approximate inference, via the method of stochastic simulation, which involves a classical sampling method called `logic sampling.' This is then followed by a discussion of likelihood weighting, which cures some of the problems involved with logic sampling. Abductive inference, so important in contemporary applications, is then discussed in detail.

Enjoying this book enormously.......2004-01-04

Rarely do I find myself reading a technical book
so carefully as this one. I always enjoy
books on Bayesian inference,
but this is the first that shows me how
to write useful algorithms. I appreciate
the level of mathematical rigor, too, for
such a new subject. Bayesian networks are what
neural networks should be, without the ad-hoc
theory and trial-and-error algorithms.

The Emotion Machine: Commonsense Thinking, Artificial Intelligence, and the Future of the Human Mind

Average customer rating:

Excellent book on thinking machines - but misleading title
The common, but wrong approach.
AI: About Intuition
Frustrating and disappointing
thinking : critic - selector model

The Emotion Machine: Commonsense Thinking, Artificial Intelligence, and the Future of the Human Mind
Marvin Minsky
Manufacturer: Simon & Schuster
ProductGroup: Book
Binding: Hardcover

Emotions | Mental Health | Health, Mind & Body | Subjects | Books

General | Psychology & Counseling | Health, Mind & Body | Subjects | Books

Cognitive | Psychology & Counseling | Health, Mind & Body | Subjects | Books

General | Science | Subjects | Books

History of Science | History & Philosophy | Science | Subjects | Books

Cognitive Psychology | Behavioral Sciences | Science | Subjects | Books

General | Behavioral Sciences | Science | Subjects | Books

Look Inside Computer Books | Trip | Specialty Stores | Books

Look Inside Health Books | Trip | Specialty Stores | Books

Look Inside Science Books | Trip | Specialty Stores | Books
Similar Items:

ASIN: 0743276639

Book Description

Our minds are working all the time, but we rarely stop to think about how they work. The human mind has many different ways to think, says Marvin Minsky, the leading figure in artificial intelligence and computer science. We use these different ways of thinking in different circumstances, and some of them we don't even associate with thinking. For example, emotions, intuitions, and feelings are just other forms of thinking, according to Minsky. In his groundbreaking new work, The Emotion Machine, Minsky shows why we should expand our ideas about thinking and how thinking itself might change in the future.

The Emotion Machine explains how our minds work, how they progress from simple kinds of thought to more complex forms that enable us to reflect on ourselves -- what most people refer to as consciousness, or self-awareness. Unlike other broad theories of the mind, this book proceeds in a step-by-step fashion that draws on detailed and specific examples. It shows that thinking -- even higher-level thinking -- can be broken down into a series of specific actions. From emotional states to goals and attachments and on to consciousness and awareness of self, we can understand the process of thinking in all its intricacy. And once we understand thinking, we can build machines -- artificial intelligences -- that can assist with our thinking, machines that can follow the same thinking patterns that we follow and that can think as we do. These humanlike thinking machines would also be emotion machines -- just as we are.

This is a brilliant book that challenges many ideas about thinking and the mind. It is as insightful and provocative as it is original, the fruit of a lifetime spent thinking about thinking.

Customer Reviews:

Excellent book on thinking machines - but misleading title.......2007-06-10

I agree with the reviewer who noted how odd it was that a book titled "The Emotion Machine" does not discuss Joseph LeDoux, even if only to refute him. But I think that the problem is with the title, not the book. I found many of Minsky's insights very helpful - it is a very good book about how machines think. And if you are not a dualist, then those insights apply to people too. The book is very well organized and clearly written, and helps you think about thinking. I especially enjoyed his discussion of qualia (although he does not use the term), and why he thinks it is not quite the problem that so many philosophers want to make it.

Minsky's main take on emotions is that emotional states are not fundamentally different from other types of thinking, and that the entire dicotomy of rationality v. emotion is misleading. He prefers to view them all as different ways of thinking - of utilizing various mental resources at one's disposal, some conscious and some not. He organizes his discussion of difficult material very well, but I wish there was more grounding in the underlying neural anatomy of human emotion.

The common, but wrong approach........2007-05-25

What is so special about emotions?
Emotions is just one kind of bechavior, among many, demonstrated by reasonable systems. It is didn't matter what kind of system it is.
Machine and human, and bacteria, or dog, all reasonable systems are subjective simply because they are isolated from direct interactions with environment and capable to demonstrate the emotional behavior.
Contrary to common opinion all live creature, not human only, are emotional.
Best regards Michael Zeldich

AI: About Intuition.......2007-04-24

My brother is a computer programmer with a computer game company and he discovered something fascinating while trying to create a simulation for the movement of a crowd.

By inputing three variables: 1) be like a common member of the group but 2) stay a certain discrete distance from your neighbor while 3) moving away when everyone gets too close, he captured the seemingly naturalist choatic looking behavior of a crowd.

The point here is that the operation of a simple set of rules can create the appearance of the phenomenon of seemingly complicated and choatic behavior.

And I don't think the point is mistaken here where Minsky and his likes consider the delicate calculus of human behavior.

While his book ends by discussing the subject of self, perhaps self is perhaps the starting point for all proper discussions of consciousness and identity. This is because -- like all animate behavior -- the existence of self is uniquely keyed to the fact of animate autonomy.

In other words, the greatest of behvaioral conundrums is perhaps the simplest. In order to to decided what to eat, do or where to go, self provides that unique user perspective to allow the necessary illumination of what inbuilt needs remain unmet and which are in the most immediate need of meeting.

An effective engineer, Mother Nature has put into excellent service the process of emotion which allows the quick, effecient recording of the relevant information.

In his classic work The Astonishing Hypothesis, Francis Crick said that self was nothing more than the current state of our neurons and ganglia. Richard Dawkins has repeatedly shown that those neurons and ganglia recieve their current structure through the explanable process of natural selection. And Minsky has done well to show that as a result of that process our brains our like programs that have been worked over many times creating occassional inconsistencies.

Indeed it is perhaps these inconsistencies themselves that lay at the very heart of intuition.

Frustrating and disappointing.......2007-04-21

I recall appreciating The Society of Mind. But in this new book, his best answer to the Mystery of Experience is, "experiencing something like a color seems simple but is actually complicated". His main answer to the mega-Mystery of the Experience of Self-Awareness is, "consciousness is a suitcase term that we use to refer to many different things". It is almost like he is pretending to not experience these mysteries himself, so that he does not have to seriously engage the question of how/why our brain/minds do these things, and under what conditions other machines might. So frustrating that it makes the book hard to read -- it might have been better to skip over these matters more, if he can't deal with them more usefully.

thinking : critic - selector model.......2007-04-01

1. We don't recognize a problem as hard until we've spent some time on it without making any significant progress. For if you can diagnose the particular type of problem you face, then you can use that knowledge to switch to a more appropriate way to think.
2. Critic-selector model of thinking: Each critic object can recognize a certain species of problem type. When a critic sees enough evidence, the critic will activate a "selector", which tries to start up a set of resources that it has learned is likely too act as a way to think that may help in this situation.
3. If a problem seems familiar, use reasoning by analogy. If it seems unfamiliar, change the way you're describing it. If it seems too difficult, divide it into several parts. If it still seems difficult, replace it by a simpler problem. If none of these work, ask someone for help.
4. If too many critics are aroused, then describe the problem in more detail. If too few critics are aroused, then make the description more abstract. If important resources conflict then you should try to discover a cause. If there has been a series of failures, then switch to a different set of critics.
5. Emotional reactions: cautious vs. reckless, unfriendly vs. amicable, visionary vs. practical, inattentive vs. vigilant, reclusive vs. sociable, and courageous vs. cowardly; each such emotional way to think can lead to different ways to deal with things-either by making you see things from new points of view or by increasing your courage or doggedness. If too many critics are active then your emotions would keep changing too quickly. And if those critics stopped working at all, then you'd get stuck in just one of states.
6. The best way to solve a problem is to already know a way to solve it. Searching extensively. When one has no better alternative, one could try to search through all possible chains of actions. But that method is not often practical because such searches grow exponentially.
7. Reasoning by analogy: when a problem reminds you of one that you solved in the past, you may be able to adapt that case to the present case situation.
8. Divide and conquer: if you can't solve a problem all at once, then break it down into smaller parts.
9. Reformulation: find a different representation that highlights more relevant information. Understand in a different way.
10. Planning: consider the set of subgoals and examine how they affect each other.
11. Techniques for problem solving: simplifying, elevating, and changing the subject.
12. More reflective ways to think: wishful thinking, self-reflection, impersonation.
13. Other modes of thinking: 1) logical contradiction: try to prove that your problem cannot be solved, and then look for a flaw in that argument. 2) Logical reasoning. We often try to make chains of deduction. 3) External representation. Drawing suitable diagrams 4) Imagination. What would happen if by simulating possible actions inside the mental models that one has built.
14. Creating higher level selectors and critics help to reduce the sizes of the searches we make.
15. Modes of thought: preparation, incubation, revelation, and evaluation.
16. Creative ideas must be combined with the knowledge and skills already possess-so it must not be too different from ideas with which we're already familiar.
17. If too may critics are active then you notice flaws to correct and spend much time repairing them and never get at the important things and people perceive us as depressed. If too many critics are turned off then you ignore alarms and concerns that would help you concentrate allowing errors and flaws. The fewer the critics active, then the fewer goals pursued, making one intellectually dull.

Neural Networks: A Comprehensive Foundation (2nd Edition)

Average customer rating:

Good info, heavy on the math, but too preachy and not for the faint of heart.
A good book with a very mathematical viewpoint
Neural Networks Foundations
Very Mathematical
Need practical examples.

Neural Networks: A Comprehensive Foundation (2nd Edition)
Simon Haykin
Manufacturer: Prentice Hall
ProductGroup: Book
Binding: Hardcover

General | Certification Central | Computers & Internet | Subjects | Books

General | Computers & Internet | Subjects | Books

French | Foreign Language Nonfiction | Nonfiction | Subjects | Books

Networking | Computer Science & Information Systems | New & Used Textbooks | Stores | Books

Electrical & Electronics | Engineering | New & Used Textbooks | Stores | Books

All Titles | Qualifying Textbooks - Fall 2007 | Stores | Books

Computers & Internet | Qualifying Textbooks - Fall 2007 | Stores | Books

Professional | Qualifying Textbooks - Fall 2007 | Stores | Books

Look Inside Computer Books | Trip | Specialty Stores | Books

Look Inside Nonfiction Books | Trip | Specialty Stores | Books

Nonfiction | French | Foreign Language Books | Specialty Stores | Books

Professional & Technical | French | Foreign Language Books | Specialty Stores | Books

All French Books | French | Foreign Language Books | Specialty Stores | Books
Similar Items:

ASIN: 0132733501

Customer Reviews:

Good info, heavy on the math, but too preachy and not for the faint of heart........2007-08-06

An excellent entry level text on the subject. The author covers most aspects of neural networks, although not quite as in depth as I had hoped in some areas. Suitable for use as a textbook if you are taking a class on the subject, or as a self study book. Gets a bit too preachy and defensive about the practicality of neural networks. The author obviously cut his teeth in NN's during the 60/70's. IMO anyone who already bought the book doesnt need convincing that neural networks work. I recommend at least a working knowledge of calculus and statistical analysis.

A good book with a very mathematical viewpoint.......2007-04-15

If you are going to start learning neural networks, this is probably the best book with which to begin. It does a good job in how it progresses through the subject. It spends two chapters introducing the subject in a very complete fashion, then five chapters more on the subject of supervised learning with neural networks, and five more chapters on unsupervised learning. The final three chapters gets off into the subject of non-linear dynamical systems.

Although the book is very complete, it is also mathematically rigorous. To really understand it from cover to cover you would need to know - both conceptually and practically - calculus, linear algebra, adaptive signal processing, and dynamical systems, since this book assumes you already know these subjects and makes heavy use of their properties. Fortunately, to get a good basic understanding of what neural networks are and what they can accomplish, you won't need to understand the entire book. I found chapters 1-7 to be fairly accessible and self-contained. It is only once you get past the subject of supervised learning in chapter eight that the mathematics and the book get particularly difficult. Another problem with the book is that it abruptly goes from a forest to a trees viewpoint of neural networks. It will be working along in a very theoretical manner for some number of pages, when suddenly, out of nowhere, it will mention something practical or show an example that clarifies a great deal. Therefore you will need to read the book carefully.

My personal recommendation is that you go through the first seven chapters of this book to get a good viewpoint of the theoretical basics of neural networks and supervised learning, and then read Jeff Heaton's "Introduction to Neural Networks with Java" to get a good practical viewpoint on the subject. Then, if you need to return to the book for the more advanced chapters, you will be better prepared. It would also be best to use this book in conjunction with taking a course on the subject. I think it would be very rough going to try to understand this book via self-study alone.

Neural Networks Foundations.......2006-08-10

This is the first book for everyone interested in the subject. A well-written and well-illutrated encyclopedia of Neural projects, including all the fundamental questions at the forefront of research in Neural Networks. I believe this is the reason for it beeing widely referenced by almost all the authors in the subject.

Very Mathematical.......2006-05-07

I used this as a textbook for a Neural Networks course I did in the second year of my undergraduate program in Mathematics and Computing.

My mathematical background till that point of time comprised Linear Algebra and upper level Calculus. This being rather 'limited' mathematical exposure, I found the book quite difficult to follow. It becomes harder when you are expected to convert the mathematical equations into working programs (without using tool-boxes or libraries, i.e.). The end-of-chapter exercises are pretty hard, and try to go beyond what the text talks about, most undergraduates may not be able be able to appreciate that. I think this is an excellent reference book for those who are pretty comfortable with Math. For undergraduates doing a first course in Neural Networks, I strongly recommend Timothy Masters' "Practical Neural Network recipes in C++". The math there is manageable, and yes, it comes with working code to make your life easier.

Need practical examples........2005-07-25

About theory, the book is good, but; it needs more practical or numerical examples, in order to get the information understandable.
There are too many concepts and ideas that without a good example, it is very hard to assimilate.
Also the computer oriented experiments in matlab, do not use the
neural network tool box, so it is not possible to get the gap to convert knowledge into computer code.
If these two recommendations are improved in a next edition, the book will become and excellent one.

thanks,

Neural Networks in Finance: Gaining Predictive Edge in the Market (Academic Press Advanced Finance Series)

Average customer rating:

More Mathematical than Technical

Neural Networks in Finance: Gaining Predictive Edge in the Market (Academic Press Advanced Finance Series)
Paul D. McNelis
Manufacturer: Academic Press
ProductGroup: Book
Binding: Hardcover

General | Popular Economics | Business & Investing | Subjects | Books

General | Business & Investing | Subjects | Books

General | Investing | Business & Investing | Subjects | Books

Math for Business | Skills | Business & Investing | Subjects | Books

Manager's Guides to Computing | Business & Culture | Computers & Internet | Subjects | Books

Network Security | Networking | Computers & Internet | Subjects | Books

General | Certification Central | Computers & Internet | Subjects | Books

General | Mathematics | Science | Subjects | Books

Look Inside Business Books | Trip | Specialty Stores | Books

Look Inside Computer Books | Trip | Specialty Stores | Books

Look Inside Science Books | Trip | Specialty Stores | Books

All Amazon Upgrade | Amazon Upgrade | Stores | Books

Business & Investing | Amazon Upgrade | Stores | Books

Computers & Internet | Amazon Upgrade | Stores | Books

Engineering | Amazon Upgrade | Stores | Books

Professional & Technical | Amazon Upgrade | Stores | Books

Science | Amazon Upgrade | Stores | Books

All Titles | Qualifying Textbooks - Fall 2007 | Stores | Books

Business & Investing | Qualifying Textbooks - Fall 2007 | Stores | Books

Computers & Internet | Qualifying Textbooks - Fall 2007 | Stores | Books

Professional | Qualifying Textbooks - Fall 2007 | Stores | Books

Science | Qualifying Textbooks - Fall 2007 | Stores | Books
Similar Items:

ASIN: 0124859674

Book Description

This book explores the intuitive appeal of neural networks and the genetic algorithm in finance. It demonstrates how neural networks used in combination with evolutionary computation outperform classical econometric methods for accuracy in forecasting, classification and dimensionality reduction.

McNelis utilizes a variety of examples, from forecasting automobile production and corporate bond spread, to inflation and deflation processes in Hong Kong and Japan, to credit card default in Germany to bank failures in Texas, to cap-floor volatilities in New York and Hong Kong.

* Offers a balanced, critical review of the neural network methods and genetic algorithms used in finance
* Includes numerous examples and applications
* Numerical illustrations use MATLAB code and the book is accompanied by a website

Download Description

This book explores the intuitive appeal of neural networks and the genetic algorithm in finance. It demonstrates how neural networks used in combination with evolutionary computation outperform classical econometric methods for accuracy in forecasting, classification and dimensionality reduction. McNelis utilizes a variety of examples, from forecasting automobile production and corporate bond spread, to inflation and deflation processes in Hong Kong and Japan, to credit card default in Germany to bank failures in Texas, to cap-floor volatilities in New York and Hong Kong.

Customer Reviews:

More Mathematical than Technical.......2006-06-13

Defiantly more of a math book than a programming guide, but that was what I was expecting. This book explains how to use neural networks in the field of finance. It does so very logically and mathematically. You are shown how to apply neural networks to many different financial problems. But you are mostly left to yourself to actually implement the neural networks on a computer system. Some example source code is provided for MathCad, which is an expensive software package you can buy separately.

If you are already comfortable with neural network programming, and are looking to learn to apply neural networks to finance, this book is great. Being a Java programmer I used the open source JOONE package to implement some of the book's examples in Java. Though JOONE is not suited to all examples in the book, it is a good start for a Java programmer.

The book shows how neural networks can be applied to many real world financial problems. The book pays particular interest to international finance. The book examines Hong Kong and Japan, examining inflation, deflation, currency volatility, and other issues.

I found the book to be very useful in giving me an introduction to neural networks in finance.

The table of contents follows:

Chapter 1: Introduction
Part 1: Econometric Foundations
Chapter 2: What Are Neural Networks?
Chapter 3: Estimation of a Network with Evolutionary Computation
Chapter 4: Evaluation of Network Estimation
Part 2: Applications and Examples
Chapter 5: Estimating and Forecasting with Artificial Data
Chapter 6: Time Series: Examples from Industry and Finance
Chapter 7: Inflation and Deflation: Hong Kong and Japan
Chapter 8: Classification: Credit Card Default and Bank Failures
Chapter 9: Dimensionality Reduction and Implied Volatility Forecasting

Artificial Intelligence: Modern Approach

Average customer rating:

Highly recommended
Worth a million
Worthwhile
Thorough book
Thick, informative & loads of diagrams

Artificial Intelligence: Modern Approach
Stuart J. Russell , and Peter Norvig
Manufacturer: Prentice Hall
ProductGroup: Book
Binding: Hardcover

General | Computers & Internet | Subjects | Books

General | Science | Subjects | Books

Look Inside Science Books | Trip | Specialty Stores | Books
Similar Items:

ASIN: 0131038052

Amazon.com

Artificial Intelligence: A Modern Approach introduces basic ideas in artificial intelligence from the perspective of building intelligent agents, which the authors define as "anything that can be viewed as perceiving its environment through sensors and acting upon the environment through effectors." This textbook is up-to-date and is organized using the latest principles of good textbook design. It includes historical notes at the end of every chapter, exercises, margin notes, a bibliography, and a competent index. Artificial Intelligence: A Modern Approach covers a wide array of material, including first-order logic, game playing, knowledge representation, planning, and reinforcement learning.

Book Description

The long-anticipated revision of this best-selling book offers the most comprehensive, up-to-date introduction to the theory and practice of artificial intelligence. Intelligent Agents. Solving Problems by Searching. Informed Search Methods. Game Playing. Agents that Reason Logically. First-order Logic. Building a Knowledge Base. Inference in First-Order Logic. Logical Reasoning Systems. Practical Planning. Planning and Acting. Uncertainty. Probabilistic Reasoning Systems. Making Simple Decisions. Making Complex Decisions. Learning from Observations. Learning with Neural Networks. Reinforcement Learning. Knowledge in Learning. Agents that Communicate. Practical Communication in English. Perception. Robotics. For those interested in artificial intelligence.

Customer Reviews:

Highly recommended.......2007-09-28

I am half way through and I like it so far. Frankly I am puzzled by other reviewers complaining about "lack of real code examples", they clearly have not read the book carefully: it comes with tons of sample code (online) written in different languages, publishers/authors simply did not want to waste the precious real estate. The book is nearly a thousand pages already.

Otherwise this is a great CS book. Yes there is some math in it, but don't be scared - there is an appendix with all necessary mathematical background you'll need (and you don't need much). I was surprised to see so much historical references in this book, it teaches you not just about most major branches of AI, but also about how they started and where originated from in a "problem -> solution" form. For instance when they talk about genetic algorithms they actually go ahead and write a comprehensive comparison of analogies between biological evolution, genes and their computer-generated counterparts referencing the original work of Darwin and others.

If you're into AI, applied mathematics or computer science, I have no doubt you'll enjoy this book: it's not too focused on something specific (and something you'd need a PhD to understand) while not too shallow and covers fairly wide spectrum of AI problems, including (!) ethical and philosophical issues like "what happens if we succeed?"

Highly recommended.

Worth a million.......2007-09-26

An author of this book is said to have commented that its writing has made him a millionaire. It is used in over 1000 universities for a simple reason, it is good. The book uses the concept of an agent to unify the formerly fragmented field of AI and to link together concepts as diverse as logic programming and ethics. It is very easy to read and touches every area of modern research interest I can think of. The problems have a nice variety of difficulties (although there are no worked-out solutions in the book) and provide a mix between theory and practice, introducing the careful student to concepts and papers not developed in the main text of the chapter. The bibliography is well laid-out and provides useful depth (one of my current research interests was sparked by reading one of the referenced papers in the 2nd chapter).

My only complaint so far (not having finished the entire book) is that some of the definitions in chapter 17's whirlwind introduction to game theory were a little vague. But, a quick look at some other sources clarified things immensely.

It is rare to find a textbook as interesting and clear as this one. If a professor is requiring that you read it, consider yourself fortunate. If you are thinking of reading it yourself, you also are blessed. Look forward to many pleasant evenings.

Worthwhile.......2007-08-23

This book is very worthwhile if you are looking into AI with the purpose of understanding the various techniques, etc. It gives a really good background, and I find it useful. The only changes I would have made (for me, not everyone else) would be to include a few short chapters on second order logic, and the basic mathematics and math terms used in the book. It assumes more knowlege in math than I have. It would also be nice if it had a "recommended reading" page, listing those texts that would be useful for an AI beginner to review in order to understand the math and logic referred to. (My degree was in 79, and I only had a very basic calculus course...not too deep...I can diffentiate, but that is all).

It would just be nice if they could list reference books for people who are math nieve.

Thorough book.......2007-01-04

This book was very thorough in many facets of Artificial Intelligence. It was a tremendous help in the class I took and will be a great reference for future years.

Thick, informative & loads of diagrams.......2007-01-04

Useful book which at first explains in great detail the history, foundations for AI and the different approaches AI takes on. Your course will probably not use all the material in the book but still makes for interesting reading. Would recommend if you can pick up a copy cheap.

Average customer rating:

May be an intermediate level
A great deal of Practical Advice
The best book to learn Neural Networks
best for beginnner
helpful

Practical Neural Network Recipes in C++
Masters
Manufacturer: Morgan Kaufmann
ProductGroup: Book
Binding: Paperback

General | Certification Central | Computers & Internet | Subjects | Books

General | Computers & Internet | Subjects | Books

General | Software | Computers & Internet | Subjects | Books

Look Inside Computer Books | Trip | Specialty Stores | Books

All Amazon Upgrade | Amazon Upgrade | Stores | Books

Computers & Internet | Amazon Upgrade | Stores | Books

Professional & Technical | Amazon Upgrade | Stores | Books

All Titles | Qualifying Textbooks - Fall 2007 | Stores | Books

Computers & Internet | Qualifying Textbooks - Fall 2007 | Stores | Books

Professional | Qualifying Textbooks - Fall 2007 | Stores | Books
Similar Items:

ASIN: 0124790402

Book Description

This text serves as a cookbook for neural network solutions to practical problems using C++. It will enable those with moderate programming experience to select a neural network model appropriate to solving a particular problem, and to produce a working program implementing that network. The book provides guidance along the entire problem-solving path, including designing the training set, preprocessing variables, training and validating the network, and evaluating its performance. Though the book is not intended as a general course in neural networks, no background in neural works is assumed and all models are presented from the ground up.
The principle focus of the book is the three layer feedforward network, for more than a decade as the workhorse of professional arsenals. Other network models with strong performance records are also included.
Bound in the book is an IBM diskette that includes the source code for all programs in the book. Much of this code can be easily adapted to C compilers. In addition, the operation of all programs is thoroughly discussed both in the text and in the comments within the code to facilitate translation to other languages.

Customer Reviews:

May be an intermediate level.......2007-08-24

This book isn't for a beginner. There're many good beginner's book for NN (or general AI), but this book delves into a bit more detail, and requires careful reading and understanding to appreciate the book.

I have given negative review for this book in the past. What I want at that time was a quick reading and code. This book is not like that. You have to have some basic knowledge in AI (at least read any introductory book once) to understand it.

I highly recommend this book for any one just got bored with introductory books on AI.

A great deal of Practical Advice.......2007-06-13

I bought my first copy of this book over two years ago. I wore it out, and I just ordered a new copy to replace it. The book is just what it says: practical, step-by-step instructions on designing and training neural nets. The author gives excellent descriptions of neural nets in plain English. He explains what they can do, what the different structures are, how to construct training sets, avoid local minima, interpret weights and evaluate performance.

An earlier reviewer claims that the code is incomplete. I am puzzled by this assertion because I had little difficulty getting it to compile and have achieved some very promising results.

I highly recommend it!

The best book to learn Neural Networks.......2006-06-09

As an undergraduate Math and Computing student, when I took up a high-level course in Neural Networks as an open elective, the only book my instructor recommended was Neural Networks by Simon Haykin. I got that book, and was soon put off by the mathematical rigour it had.
It was sometime later that I came across Practical Neural Network Recipes in C++ by Masters'. This, by all standards, is an exceptionally well written book.
It has the complete code for a neural network application, including Conjugate Gradient based back-propagation, Simulated Annealing and Genetic Algorithm powered optimisation, and much more. The code, although not very object-oriented, is clear and easy to follow. Undergraduates with a limited knowledge of mathematics will most certainly appreciate the way Masters' deals with the underlying concepts behind neural networks training and use. He simplifies the mathematical equations, and the code listings serve to see the math in action. The more mathematically mature can look into the excellent references provided in the text.
When much later in the course I went on to study Recurrent Networks (RNNs, which Masters' doesn't cover in his book), I found myself going back to Masters' when I had to implement algorithms for RNN training. This is one book that will teach you to convert complex mathematical equations into working code. Its a skill that is of much importance to most computational science students. This book is a must have for all neural networks students and practitioners alike.

best for beginnner.......2005-08-09

I found it is best for beginner with best suited examples. It teaches as if teacher is with you and the way examples seleted is the best. After completion of this book you feel as if expert in subjet with true fundamental knowledge in ANN programming. Best book to start with ANN Programming

helpful.......2005-07-16

I bought this book ages ago without any knowledge of neural nets and used the book and accompanying neutral.exe executable to conduct a research study. I am not a C/C++ programmer so I cannot speak to the clarity or quality of the code but I did carefully read the text of the book and I found it very helpful in understanding neural nets and applying them. (Readers might complement this book with a good, practical social sciences text on applying regression... for example, Masters and the AI community seemed to have a poor grasp of the phenomenon of "shrinkage" in noisy environments.)

I read a review here claiming that some of Master's source is not on the disc. I cannot refute that he had trouble but I successfully compiled Master's code on my Linux machine yesterday. [I had to comment out the conio inclusions, replace getch() (and getch ()) with getchar(), and remove the calls to kbhit()... maybe this is the source of that person's problems.] The resulting executable linked and seemed to run correctly.

Average customer rating:

Thinking as an internalized movement!
Readable and wide-ranging, but all from just one theoretical perspective
Amazing Neuroscience synthesis!
read it.
Very worthwhile

I of the Vortex: From Neurons to Self
Rodolfo R. Llinas
Manufacturer: The MIT Press
ProductGroup: Book
Binding: Hardcover

Neuropsychology | Psychology & Counseling | Health, Mind & Body | Subjects | Books

General | Psychology & Counseling | Health, Mind & Body | Subjects | Books

Anatomy | Biological Sciences | Science | Subjects | Books

General | Evolution | Science | Subjects | Books

General | Medicine | Subjects | Books

Look Inside Health Books | Trip | Specialty Stores | Books

Look Inside Science Books | Trip | Specialty Stores | Books
Similar Items:

ASIN: 0262122332

Amazon.com

What is it about neuroscience that graces its practitioners with humility? Rodolfo Llinas of the NYU School of Medicine continues this tradition of quietly tackling the deepest issues in I of the Vortex. This exposition on the evolution and development of consciousness is accessible and intriguing enough to interest readers more philosophically than scientifically oriented. Grounded in research, the book posits our awareness as an artifact of the cortico-thalamic binding of perceptions and movements in synchrony; Llinas uses this theory as a launching pad for more far-reaching considerations of selfhood all the more relevant for their correlation with the facts.

Charmingly illustrated with artistic and scientific images cleverly supporting the arguments, the book is a quick if challenging read, and it explains all the scientific basics for those approaching from the humanities. Synthesizing evolution, philosophy, and neuroscience is becoming an increasingly popular endeavor for introspective eggheads, and we should be grateful: the question of consciousness affects us all and touches on every other field, from theology to particle physics. I of the Vortex is a welcome contribution to the theory of mind and essential reading for the introspective. --Rob Lightner

Book Description

In I of the Vortex, Rodolfo Llinas, a founding father of modern brain science, presents an original view of the evolution and nature of mind. According to Llinas, the "mindness state" evolved to allow predictive interactions between mobile creatures and their environment. He illustrates the early evolution of mind through a primitive animal called the "sea squirt." The mobile larval form has a brainlike ganglion that receives sensory information about the surrounding environment. As an adult, the sea squirt attaches itself to a stationary object and then digests most of its own brain. This suggests that the nervous system evolved to allow active movement in animals. To move through the environment safely, a creature must anticipate the outcome of each movement on the basis of incoming sensory data. Thus the capacity to predict is most likely the ultimate brain function. One could even say that Self is the centralization of prediction.

At the heart of Llinas's theory is the concept of oscillation. Many neurons possess electrical activity, manifested as oscillating variations in the minute voltages across the cell membrane. On the crests of these oscillations occur larger electrical events that are the basis for neuron-to-neuron communication. Like cicadas chirping in unison, a group of neurons oscillating in phase can resonate with a distant group of neurons. This simultaneity of neuronal activity is the neurobiological root of cognition. Although the internal state that we call the mind is guided by the senses, it is also generated by the oscillations within the brain. Thus, in a certain sense, one could say that reality is not all "out there," but is a kind of virtual reality.

Customer Reviews:

Thinking as an internalized movement!.......2007-06-24

Jorge Borges wrote, "I am not sure that I exist, actually. I am all the writers that I have read, all the people that I have met, all the women that I have loved; all the cities that I have visited, all my ancestors... Perhaps I would have liked to be my father, who wrote but has the decency of not publishing".
In the book "I of the vortex" Rodolfo Llinas gives another perspective on who am "I" and where "I" comes from, looking into the deep and dark recesses of the brain as a neuroscientist and physician, leaving God out from the game, unlike his maestro John Eccles, a dedicated theist, who wrote that "there is a Divine Providence operating over and above the materialistic happenings of biological evolution".
The ultimate thesis Llinas nominates is: "thinking is an internalized movement". He makes his point very clearly, based on his extensive knowledge and experience both as a scientist and writer. Perhaps thinking is an internalized movement? Perhaps not! The book "I of the vortex" is the ultimate read for those who ask Questions. An excellent book.

Readable and wide-ranging, but all from just one theoretical perspective.......2006-10-23

What is the "self" in neural terms? Few would be bold enough to claim an answer to that question. Yet in "I of the Vortex: From Neurons to Self," Rodolfo Llinas sketches a very compelling picture of how the self, consciousness, and intelligence may arise in the brain.

Essentially, Llinas's argument goes as follows. First, brains are really only found in animals that move (so, obviously, plants do not have brains). In fact, at least one animal - the sea squirt - actually devours its own brain once it no longer needs to move. Although simple movements might be caused by oscillatory pattern generators in the spinal cord, the brain is necessary for more complex, sensory-guided movement. Why should this be so?

The answer Llinas provides is prediction, or in other words, a sensorimotor internal model of the world based on "dt lookahead" functions, interfacing the motor and sensory systems. Synchronized oscillations from the cerebellum (Llinas's area of expertise) carry out the motor-side of this computation, giving rise to the characteristic 8-12 Hz periodicity of the neural signals that command voluntary movements. At a higher frequency (40 Hz), other neuronal oscillations throughout the thalamocortical system serve to bind sensory representations together. And the subjective, cognitive correlate of the intersection of these oscillations is no less than the self: "this temporally coherent event that binds, in the time domain, the fractured components of external and internal reality into a single construct is what we call the 'self.'"

But wait, doesn't that mean that all animals have a sense of "self"- even the lowly sea squirt (at least before it eats its brain)? It would seem so. But that's not the end of Llinas's more controversial claims. Llinas also suggests that neural networks explain "very little concerning the actual functioning of the nervous system itself," advocating instead the idea that most of our cognitive abilities are genetically prewired at birth. Along these lines, Llinas endorses Chomsky's idea that genes may to a large extent determine language, and furthermore that language exists in many species besides homo sapiens.

It is here that "I of the Vortex" starts to seem more like a manifesto than a careful scientific analysis. For example, after introducing the basics of neurophysiology and comparative neurology in the first half of the book, Llinas skips the cognitive level of analysis almost altogether and starts extrapolating directly to issues of consciousness, awareness, and selfhood. This bias against direct investigations of cognition (something arguably very important for understanding consciousness) is nowhere more apparent than when he refers to cognitive neuroscience as "neophrenology." But without this important middle-level of analysis, Llinas is mostly shooting from the hip in the second half of the book - and aiming for concepts that are simply too far removed from Llinas's expertise in cellular neurophysiology.

On the whole, Llinas has done an admirable job of outlining one particular view of how neuronal dynamics may give rise to consciousness in an embodied cognition framework. In this sense, "I of the Vortex" makes an excellent companion to other high-level introductions to cognitive neuroscience.

Amazing Neuroscience synthesis!.......2005-08-14

The book presents an amazing Neuroscience synthesis that covers all the aspects: from ions to synergistic systems. It gives a thought-provoking explanation of the origin of the brain through evolution. It also explains the concepts of 'qualias' and 'fixed action patterns' in such an integrative manner and concludes that everything was perfectly made to synergistically create our predictive brains.

read it........2004-09-07

If you are going to read one book about neuroscience, consciousness, or the meaning of life, this should be it. Dr. Llinas has made some unusually innovative and profound assertions about how the self ("soul") might be generated from the mechanical workings of the brain. While the answer to the hard problem of consciousness remains elusive, I can honestly say after having read many books on the subject, that this is as close as it gets.

Very worthwhile.......2002-05-20

The author presents quite a plausible theory of mind, based on his work as a neuroscientist. I suspect Llinas is very much on the right track to illuminating the physical basis of consciousness.

Building chapter-by-chapter simultaneously on the apparent evolutionary development from the simplest neuronal system to the centralized brain, and on the results of brain scans and other experiments, Llinas brings us calmly and reasonably to the resultant human mind of today.

For Llinas, consciousness is the synchronized 40Hz firing of regions of the cortex over time. That is, consciousness is not just a given pattern of firing in 3-space, but is a 4-space relation. That additional dimension of time multiplies enormously the potential number of brain patterns that could occur in an individual. But it also makes the topic that much harder to study.

The writing feels like it has been written by someone who knows alot: there are many points where conceptual connections are not made entirely explicit (because it probably seemed so self-evident to Llinas) and the reader must fill in those gaps. Also, some of his non-neurologic language is quite technical: the description of the "self" as a calculated eigenvector, or the "vortex" which is essentially an attractor (as known in mathematics), that can make Llinas sound like a cold, hard-nosed scientist.

However, Llinas is refreshingly 'human'. For him, it is quite reasonable to assume (as a common consequence of evolution and similarity of brain structure) that many other species have forms of consciousness. Indeed, he devotes an entire chapter to qualia, and contends that qualia exist as essential brain feature, not only for humans but for cats and dogs and most other animals with brains of the same evolutionary genre (and that even in the case of invertebrate (octopus) brains he argues that the burden of proof is on those who would deny qualia).

Book Description

This exciting addition to the McGraw-Hill Series in Computer Science focuses on the concepts and techniques that contribute to the rapidly changing field of machine learning--including probability and statistics, artificial intelligence, and neural networks--unifying them all in a logical and coherent manner. Machine Learning serves as a useful reference tool for software developers and researchers, as well as an outstanding text for college students.

Customer Reviews:

Outstanding.......2007-09-12

I read this book about 7 years ago while in the PhD program at Stanford University. I consider this book not only the best Machine Learning book, but one of the best books in all of Computer Science. It covers every branch of ML I know of and it covers it really well. I found Mitchell's chapter on Neural Networks more insightful than an entire book on NN's that I read. I also found his chapter on Reinforcement Learning more useful and better explained than an entire book on Reinforcement Learning that I also read. The other chapters cover other ML topics at the same level of quality and rigor.

The author did an amazing job in covering the breadth and depth of ML in less than 500 pages. I hope he will write a new edition to cover the advances that happened in the last decade.

Great Start to Machine Learning.......2007-08-27

I have used this book during my masters and found it to be an extremely helpful and a gentle introduction to the thick and things of machine learning applications. The various chapters are nicely paced with helpful problems at the end. Another great thing about the book is treatment of detailed examples with each concept and that the author carefully ties various concepts as they arise, with not just new, but also examples from previous chapters, which helps the user to understand different concepts applied to same problems thereby making clear difference between different methods. Also the author has a dedicated website with updated errata and notes, which is also very helpful! Having said that, I think the book is an introduction to various machine learning methods and one can easily follow on the references listed for detailed treatment of relevant topics.

Best book I've seen on topic.......2007-01-31

I have this book listed as one of the best and most interesting I've ever read. I loved the book just as much as I loved the course we used it in.

I have a genuine interest in AI and especially Machine Learning and this book both inspired me as well as clared some things up for me. Like how the spectrum of different known methods differ in their appoach of different problems.

This book is also very concise and well written, without being too mathematical. Making it very easy to read and understand.

Ever since I took that course I keep returning to this book as a reference when I have a related problem to solve, or just bothering my mind.

Highly recommended!

too expensive I would say.......2006-10-13

great book if you wanna start sth anywhere in machine learning, but it is toooooo expensive.

Excellent book, concise and readable.......2006-06-22

This is a great book if you're starting out with machine learning. It's rare to come across a book like this that is very well written and has technical depth. The writing is to the point, maybe even a bit terse, but all that you need to know is in there. It's a bit old so doesn't cover kernel methods or SVM's but is still a great first machine learning book.

Books:

Books Index

Books Home

Recommended Books