Amazon.com
This book comprehensively discusses the neural network models from a statistical mechanics perspective. It starts with one of the most influential developments in the theory of neural networks: Hopfield's analysis of networks with symmetric connections using the spin system approach and using the notion of an energy function from physics. Introduction to the Theory of Neural Computation uses these powerful tools to analyze neural networks as associative memory stores and solvers of optimization problems. A detailed analysis of multi-layer networks and recurrent networks follow. The book ends with chapters on unsupervised learning and a formal treatment of the relationship between statistical mechanics and neural networks. Little information is provided about applications and implementations, and the treatment of the material reflects the background of the authors as physicists. However the book is essential for a solid understanding of the computational potential of neural networks. Introduction to the Theory of Neural Computation assumes that the reader is familiar with undergraduate level mathematics, but does not have any background in physics. All of the necessary tools are introduced in the book.
Customer Reviews:
Clear and logical exposition.......2007-08-18
It's not the latest book on this topic, so today, there are other texts that have more recent developments to be sure. I originally read this text about 15 years ago. But what I got from this book, that I didn't get from most, are important insights and clear understanding of the material that's covered. The authors have a deep understanding, and have teaching as their goal in writing. Most other texts in this area are lacking in one or both of those characteristics, and aren't worth the paper they are printed on.
Introduction to the Theory of Neural Computation.......2000-10-06
This book is written from a mathematical perspective. The book introduces the Hopfield Neural Network with history and applications. The authors solve the network problem and develop the Hebb Rule. Links are made to Ising Spin models and stochastic problems. I find this book to be one of the best written mathematical guides for Neural Networks.
A Broad Survey.......1997-11-08
This was a good survey, and well-grounded mathematically. It is kind of scattershot, and if you primarily want to do practical projects like predicting financial markets, a lot of the sections won't be relevant. But if you want a broad-based approach, emphasizing a variety of network designs fro different purposes, this book is very good.
Average customer rating:
- Wonderful Book!
- Stimulating introduction and review of ICA
- Outstanding
- The best introduction on the subject
- James Stone's monograph: 'Independent Component Analysis'
|
Independent Component Analysis: A Tutorial Introduction (Bradford Books)
James V. Stone
Manufacturer: The MIT Press
ProductGroup: Book
Binding: Paperback
 Neural Networks
| Artificial Intelligence
| Computer Science
| Computers & Internet
| Subjects
| Books
General
| Computers & Internet
| Subjects
| Books
Neuropsychology
| Psychology & Counseling
| Health, Mind & Body
| Subjects
| Books
General
| Science
| Subjects
| Books
Set Theory
| Pure Mathematics
| Mathematics
| Science
| Subjects
| Books
Cognitive Psychology
| Behavioral Sciences
| Science
| Subjects
| Books
General
| Behavioral Sciences
| Science
| Subjects
| Books
General
| Medicine
| Subjects
| Books
Cognitive Psychology
| Behavioral Sciences
| Professional Science
| Professional & Technical
| Subjects
| Books
Cognitive Science
| Behavioral Sciences
| Professional Science
| Professional & Technical
| Subjects
| Books
Set Theory
| Pure Mathematics
| Mathematics
| Professional Science
| Professional & Technical
| Subjects
| Books
All Titles
| Qualifying Textbooks - Fall 2007
| Stores
| Books
Computers & Internet
| Qualifying Textbooks - Fall 2007
| Stores
| Books
Medicine
| Qualifying Textbooks - Fall 2007
| Stores
| Books
Professional
| Qualifying Textbooks - Fall 2007
| Stores
| Books
Science
| Qualifying Textbooks - Fall 2007
| Stores
| Books
Similar Items:
-
Independent Component Analysis
-
Principal Component Analysis
-
Electric Fields of the Brain: The Neurophysics of EEG
-
An Introduction to the Event-Related Potential Technique (Cognitive Neuroscience)
-
Event-Related Potentials: A Methods Handbook (Bradford Books)
ASIN: 0262693151 |
Book Description
Independent component analysis (ICA) is becoming an increasingly important tool for analyzing large data sets. In essence, ICA separates an observed set of signal mixtures into a set of statistically independent component signals, or source signals. In so doing, this powerful method can extract the relatively small amount of useful information typically found in large data sets. The applications for ICA range from speech processing, brain imaging, and electrical brain signals to telecommunications and stock predictions.
In Independent Component Analysis, Jim Stone presents the essentials of ICA and related techniques (projection pursuit and complexity pursuit) in a tutorial style, using intuitive examples described in simple geometric terms. The treatment fills the need for a basic primer on ICA that can be used by readers of varying levels of mathematical sophistication, including engineers, cognitive scientists, and neuroscientists who need to know the essentials of this evolving method.
An overview establishes the strategy implicit in ICA in terms of its essentially physical underpinnings and describes how ICA is based on the key observations that different physical processes generate outputs that are statistically independent of each other. The book then describes what Stone calls "the mathematical nuts and bolts" of how ICA works. Presenting only essential mathematical proofs, Stone guides the reader through an exploration of the fundamental characteristics of ICA.
Topics covered include the geometry of mixing and unmixing; methods for blind source separation; and applications of ICA, including voice mixtures, EEG, fMRI, and fetal heart monitoring. The appendixes provide a vector matrix tutorial, plus basic demonstration computer code that allows the reader to see how each mathematical method described in the text translates into working Matlab computer code.
Customer Reviews:
Wonderful Book!.......2007-08-16
Eases the reader gradually through the foundations of ICA and treats various published methods in a contrasting manner. No other reference is needed while reading the book; he even gives the pronounciation of some of the greek letters in footnotes.
Stimulating introduction and review of ICA.......2007-07-03
This excellent book introduces the reader in the field of Independent Component Analysis providing the necessary fundamentals to understand and apply the different methods. The book also makes interesting links to other techniques. The author has succeeded at writing a very didactic text, not an easy task given the complexity of the matter, and at transmitting his enthusiasm to the reader.
I've enjoyed this book, which has been not only an introduction to ICA but which has brought me into ICA, stimulating my own experimentation with the technique.
Outstanding.......2006-11-27
Without this book I would never have understood the basics and finesses of ICA. Even if readers ar highly skilled in math reading this book will set out mile'stones' that will enhance the understanding of the ICA- problem, -tools and -possibilities.
Dr. G. Otte
The best introduction on the subject.......2006-05-05
I can't stress how reader friendly this book is. It is by far the best introduction on component analysis. It is written in such a way that those with a weaker math background can understand it while those with years of experience will not be bored, at certain times it even reads like a story.
It addition to being readable the book contains an impressive amount of content for its size. This content is presented in an organized manner, and in such a way that the user can immediately apply the techniques to their own problems.
If you are interested in independent component analysis or one of its relatives I highly recommend this valuable, reasonably price book.
James Stone's monograph: 'Independent Component Analysis'.......2006-01-10
James Stone's monograph is a refreshing new book amongst the many other `new books' on Independent Component Analysis (ICA). The author brings his teaching experience to present the theory and practice of ICA in a highly accessible form using a duplication of words and straight-forward mathematics.
Particular attention is given in the earlier chapters to the description of the linear signal mixing process giving the Reader a good basis for understanding the fundamental assumptions upon which ICA and its application to Blind Source Separation are based.
The book is aimed at the Reader with a technical but not necessarily formal mathematics background. Illustrative examples and functional algorithms in MatLab are frequent and references are made to the author's available electronic resources. As such it is suitable to both the newcomer to ICA, and to the more expert engineer or scientist.
This Reviewer rates this book very highly.
Book Description
Bring a robot to life without programming or assembly language skills!
There’s never been a better time to explore the world of the nearly human. With the complete directions supplied by popular electronics author John Iovine, you can:
• Build your first walking, talking, sensing, thinking robot
• Create 12 working robotic projects, using the fully illustrated instructions provided
• Get the best available introduction to robotics, motion control, sensors, and neural intelligence
• Put together basic modules to build sophisticated ‘bots of your own design
• Construct a robotic arm that responds to your spoken commands
• Build a realistic, functional robotic hand
• Apply sensors to detect bumps, walls, inclines , and roads
• Give your robot expertise and neural intelligence
You geteverything you need to create 12 exciting robotic projects using off-the-shelf products and workshop-built devices, including a complete parts list. Also ideal for anyone interested in electronic and motion control, this cult classic gives you the building blocks you need to go practically anywhere in robotics.
Customer Reviews:
Very good Hobbiest book.......2006-11-10
Plenty of information for make very good projects, unfortunately for my taste, the autor only works with PIC microcontrollers, perhaps a very good book
Very good book!!.......2003-09-18
This book is great for the beginner. Iovine explains the subject matter in a way that makes it exciting and fun. He has a way of getting the exciting vision of building robots across to the reader. The book makes it easy to get parts needed for the projects from the authors web site. I'm really looking forward to his new book, Pic Robotics!!!
I'm glad I finally found a decent book on pics!.......2002-06-03
This was the 3rd book I purchased on pics. The other 2 books - one by Myke Predko (awful), the other by David L. Benson (dissapointing.)
I wish this had been the first. Although not geared specificly towards pics, that was my reason for buying it. I was interested in pics and robotics; so this book was right up my alley.
Admittedly the book has numerous plugs for a company the guy obviously works for, owns, or gets kickbacks from! And he wants you to put out a considerable about of cash from the get go to purchase items he wants you to use in order to follow along with him. However, that doesn't bother me. I never build any projects I see in these type of books. I only use them for learning - I build my own projects.
This book did teach me quite a bit about pics. Which was my goal. He didn't bog you down with the history or innards of pics like other books. Which I am not interested in. The book was a great mixture of hardware and software topics...
I would recommend this book to anyone interested in pics... Subsequently I purchased another book by him simply because I saw his name on it and I wasn't dissapointed! I'm looking forward to other books by John Iovine in the future...
Projects can be a bit pricy........2002-03-13
The illustrations and text I found to be very helpful for a project I was working on, but the supplies the book recommends can usually de difficult to find, and can tend to be a bit pricy.
I recommend visiting a local toy store after deciding on a project, and buying toys with the parts you need. Its more fun to make one thing into another anyway.
This book has changed my life........2002-01-23
I bought this book with the humble desire of creating a simple companion. After I finished, the Creation turned on me and my family and reprogrammed my VCR. It then proceeded to change the message on my answering machine. It somehow convinced my Nissan truck not to allow me inside. I fear for my life. How could I have let it go this far? All I really wanted was a cute little Furby but I ended up with a cyber-monster with dreams of wiping out humans and creating a robotic Utopian Hell.....other than that, the book was pretty cool.
Book Description
Introduction to Neural Networks in Java introduces the Java programmer to the world of Neural Networks and Artificial Intelligence. Neural network architectures such as the feedforward backpropagation, Hopfield, and Kohonen networks are discussed. Additional AI topics, such as Genetic Algorithms and Simulated Annealing, are also introduced. Practical examples are given for each neural network. Examples include the Traveling Salesman problem, handwriting recognition, fuzzy logic and learning mathematical functions. All Java source code can be downloaded online. In addition to showing the programmer how to construct these neural networks, the book discusses the Java Object Oriented Neural Engine (JOONE). JOONE is a free open source Java neural engine.
Customer Reviews:
A bit disappointed because I expected more from this book........2006-06-19
I have been reading through the book. Actually it provides very clear explanations, but I had the impression the author talks too much and keep saying the same things over and over again. The book could be half its volume with the same content of knowledge. Besides the provided examples are a bit too simple and obvious.
Nothing much to put under the tooth. After reading it I felt left with my hunger for something deeper and more consistent. The algorithms provided also merely implement and stick to the few examples introduced. On the course of the book, the author wanders from the main point which is first and foremost to discuss neural networks under all angles. He unexpectedly brings up Fuzzy logic and Genetic algorithms which is not what the book title purports to talk about: a bit of confusion.
Overall there is a bit of deception, but indeed the book does what its title says : it is really just an "introduction" to Neural Networks with Java and nothing more. I would recommend it to somebody seeking to embrace the field and who is really a beginner in the domain.
Excellent practical book on neural networks using Java.......2006-03-27
Programming Neural Networks in Java will show the intermediate to advanced Java programmer how to create neural networks. This book attempts to teach neural network programming through two mechanisms. First the reader is shown how to create a reusable neural network package that could be used in any Java program. Second, this reusable neural network package is applied to several real world problems that are commonly faced by programmers. This book covers such topics as Kohonen neural networks, multi layer neural networks, training, back propagation, and many other topics. The content of the book is as follows:
Chapter 1: An Introduction to Neural Networks
The structure of neural networks will be briefly introduced in this chapter. Also discussed is the history of neural networks, since it is important to know where neural networks came from, as well as where they are ultimately headed. Finally, there is a broad overview of both the biological and historic context of neural networks.
Chapter 2: Understanding Neural Networks
A neural network can be trained to recognize specific patterns in data. This chapter will teach you the basic layout of a neural network and end by demonstrating the Hopfield neural network, which is one of the simplest forms of neural network.
Chapter 3: Using Multilayer Neural Networks
You will see how to use the feed-forward multilayer neural network and two ways that you can implement such a neural network. The chapter begins by examining an open source neural network engine called JOONE. JOONE contains a neural network editor that allows you to quickly model and test neural networks.
Chapter 4: How a machine learns
Every learning algorithm involves somehow modifying the weight matrices between the neurons. This chapter examines some of the more popular ways of adjusting these weights.
Chapter 5: Understanding Back Propagation
This chapter examines one of the most common neural network architectures-- the feed foreword back propagation neural network.
Chapter 6: Understanding the Kohonen Neural Network
The Kohonen neural network contains no hidden layer. The Kohonen neural network differs from the feedfroward back propagation neural network in several important ways. This chapter examines the Kohonen neural network and how it is implemented.
Chapter 7: Optical Character Recognition
This chapter develops an example program that can be trained to recognize human handwriting. It is not a program that can scan pages of text. Rather this program will read character by character, as the user draws them. This function will be similar to the handwriting recognition used by many PDA's.
Chapter 8: Understanding Genetic Algorithms
A chapter on an AI technology unrelated to neural networks.
Chapter 9: Understanding Simulated Annealing
A second AI technology that can be used to train neural networks.
Chapter 10: Eluding Local Minima
One of the most fundamental flaws is the tendency for the backpropagation training algorithm to fall into a "local minima". A local minimum is a false optimal weight matrix that prevents the backpropagation training algorithm from seeing the true solution. This chapter shows how to use certain training techniques to supplement backpropagation and elude local minima.
Chapter 11: Pruning Neural Networks
This chapter examines several algorithms that modify the structure of the neural network. This structural modification will not generally improve the performance of the neural network, but makes it more efficient. If a particular neuron's connection to other neurons does not significantly affect the output of the neural network, the connection will be pruned.
Chapter 12: Fuzzy Logic
Fuzzy logic is a branch of AI not directly related to the neural networks examined so far. Fuzzy logic is often used to process data before it is fed to a neural network, or to process the outputs from the neural network. Fuzzy logic is examined in reference to removing SPAM from emails.
Appendix A: JOONE Reference
Appendix B: Mathematical Backgrounder
Appendix C: Using the Examples on a Windows System
Appendix D: Using the Examples on a UNIX System
This book is currently available online. Since Amazon throws out reviews with web addresses in them, suffice it to say that you just need to type "HeatonResearch" into Google. The 2nd address is the one you want. This book couples accessible instruction with plenty of code that you can lift to make your own neural network applications. I highly recommend it.
Unique book.......2006-01-31
I have received my copy of the book and I can't put it down. It has been great help with my AI research at the University. I have the other book from the same author "Programming Spiders, Bots and Aggregators in Java" and I have the same comments for both. Both are easy to read, have precise information and great code. Chapter 7 of this book "OCR with Kohonen Neural Network" makes the book more than worth it. Great stuff. I hope the author does not stop and keep writting books like these. I recommend this book for anyone interested in learning AI and also experienced programmers alike. The author makes though topics seem easy. Highly recommended.
Book Description
Though mathematical ideas underpin the study of neural networks, the author presents the fundamentals without the full mathematical apparatus. All aspects of the field are tackled, including artificial neurons as models of their real counterparts; the geometry of network action in pattern space; gradient descent methods, including back-propagation; associative memory and Hopfield nets; and self-organization and feature maps. The traditionally difficult topic of adaptive resonance theory is clarified within a hierarchical description of its operation. The book also includes several real-world examples to provide a concrete focus. This should enhance its appeal to those involved in the design, construction and management of networks in commercial environments and who wish to improve their understanding of network simulator packages. As a comprehensive and highly accessible introduction to one of the most important topics in cognitive and computer science, this volume should interest a wide range of readers, both students and professionals, in cognitive science, psychology, computer science and electrical engineering.
Customer Reviews:
Just what I needed.......2007-09-27
This book got me started with neural networks. Prior to this book I had only read some articles and didn't quite know what was going on. Now I have an application that makes football predictions straight up. It does not go overboard with math but there are certainly some deep sections. Even if you are using someone else's neural network objects, this is a good read to help you understand the concepts behind NN and what type you want to use.
Concise but explanatory.......2006-02-18
This is one of the best written books on NN. This book has that rare quality of being succinct but clearly written so that it can be understood by reasonably mathematical minded individual.
It covers most of the basic topics (back propagation, feed forward, Hopfield nets etc) and gives idiosyncrasies of the field. It also gives you a simple but accurate understanding of the mathematics and algorithms for the field.
I would highly recommend this book to anyone just entering into the field and has some mathematical background.
A good introduction without serious math.......2001-04-01
I checked this book out of my university library and was pleasently suprised, although this is by no means a comprehensive book for those who are taking a high level course on AI/neural nets it serves as a very good and complete introduction to those of us who wish to learn more about a very interesting area of computing. After an introduction and review of notation, several basic models are introduced starting with the TLU and progressively presenting more advanced models.
The book is not aimed towards computer science students, and also has in mind other backgrounds. It does however require a sufficient background in science/math (basic algebra and geometry, vectors).
Average customer rating:
|
Introduction to Applied Fuzzy Electronics
Ahmad M. Ibrahim
Manufacturer: Prentice Hall
ProductGroup: Book
Binding: Hardcover
Fuzzy Logic
| Algorithms
| Programming
| Computers & Internet
| Subjects
| Books
Logic
| Software Design, Testing & Engineering
| Programming
| Computers & Internet
| Subjects
| Books
Neural Networks
| Artificial Intelligence
| Computer Science
| Computers & Internet
| Subjects
| Books
Circuit Components
| Circuitry
| Computer Science
| Computers & Internet
| Subjects
| Books
Circuits
| Electrical & Electronics
| Engineering
| Professional & Technical
| Subjects
| Books
| Design
| Digital Integrated Circuit Design
| General
| Integrated
| Microwave
General
| Electrical & Electronics
| Engineering
| Professional & Technical
| Subjects
| Books
Digital Design
| Electrical & Electronics
| Engineering
| Professional & Technical
| Subjects
| Books
General
| Electronics
| Electrical & Electronics
| Engineering
| Professional & Technical
| Subjects
| Books
General
| Reference
| Subjects
| Books
General
| Arts & Photography
| Subjects
| Books
Applied
| Physics
| Science
| Subjects
| Books
Look Inside Art Books
| Trip
| Specialty Stores
| Books
Look Inside Computer Books
| Trip
| Specialty Stores
| Books
Look Inside Reference Books
| Trip
| Specialty Stores
| Books
Look Inside Science Books
| Trip
| Specialty Stores
| Books
All Titles
| Qualifying Textbooks - Fall 2007
| Stores
| Books
Arts & Photography
| Qualifying Textbooks - Fall 2007
| Stores
| Books
Computers & Internet
| Qualifying Textbooks - Fall 2007
| Stores
| Books
Professional
| Qualifying Textbooks - Fall 2007
| Stores
| Books
Reference
| Qualifying Textbooks - Fall 2007
| Stores
| Books
Science
| Qualifying Textbooks - Fall 2007
| Stores
| Books
ASIN: 0132064006 |
Book Description
KEY BENEFIT: This book provides a self-contained, compact introduction to fuzzy logic from an applied electronics point of view. It presents fuzzy electronics as a generalization of digital electronics with the goal of making fuzzy logic easily accessible to practicing engineers and students alike.
Average customer rating:
- Great Content, Author Can't Explain Clearly Though
- At times cryptic, but nevertheless marvellous
- Hard Science
- An excellent textbook for this rapidly changing field.
|
Introduction to Artificial Life
Christoph Adami
Manufacturer: Springer
ProductGroup: Book
Binding: Hardcover
Artificial Life
| Artificial Intelligence
| Computer Science
| Computers & Internet
| Subjects
| Books
General
| Artificial Intelligence
| Computer Science
| Computers & Internet
| Subjects
| Books
Neural Networks
| Artificial Intelligence
| Computer Science
| Computers & Internet
| Subjects
| Books
General
| Computers & Internet
| Subjects
| Books
General
| Evolution
| Science
| Subjects
| Books
General
| Science
| Subjects
| Books
General
| Physics
| Science
| Subjects
| Books
General
| Physics
| Professional Science
| Professional & Technical
| Subjects
| Books
General
| Computer Science & Information Systems
| New & Used Textbooks
| Stores
| Books
Artificial Intelligence
| Computer Science & Information Systems
| 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
Science
| Qualifying Textbooks - Fall 2007
| Stores
| Books
Look Inside Computer Books
| Trip
| Specialty Stores
| Books
Look Inside Science Books
| Trip
| Specialty Stores
| Books
Similar Items:
-
Artificial Life: An Overview (Complex Adaptive Systems)
-
Artificial Life Models in Software
-
Artificial Life: A Report from the Frontier Where Computers Meet Biology
-
An Introduction to Genetic Algorithms (Complex Adaptive Systems)
ASIN: 0387946462 |
Book Description
Life is so diverse and complex that is seems impossible to extract the general principles governing each individual living system. Fortunately, however, the unrelenting growth of the power of modern computers has opened up entirely unexpected avenues of opportunity for us in exploring the construction of artificial living systems. This has created the possibility to design and conduct dedicated experiments with these systems, and has generated interest in the idea of formulating a set of "general principles of the living state" which are quite independent of a particular implementation. Such a "theory of living systems" might equally well-predict the outcome of experiments performed on the protean living system which gave rise to life on earth, e.g., and RNA world, and those worlds in which information is coded in binary strings compiled to programs that have the ability to self-replicate: thus and instance of "Artificial Life." This book and CD-ROM have been developed in a lab-oriented course taught at Cal Tech in 1995 and 1996, and simultaneously augmented by Artificial Life research conducted there. The courses have been attended by an interdisciplinary group of students from backgrounds in physics, computer science, and the computational neural sciences. Pre- requisite understanding of statistical physics and thermodynamics, basic biology, as well as familiarity with computer architectures and scientific computing techniques are assumed. This project is an attempt to bring together the necessary theoretical groundwork for understanding the dynamics of systems of self-replicating information, as well as the result from initial experiments carried out with artificial living systems based on this paradigm.
Customer Reviews:
Great Content, Author Can't Explain Clearly Though.......2000-11-14
I bought this book to understand the mathematics and physics in A-Life and Complexity. Instead I found this book very long winded and difficult to comprehend exactly what was trying to be said. The content and layout of the book is great, just wish a better writer had been the author of this book. Lots of fancy, big words that are not needed to get the basic points across. Very hard to understand what is being said. It takes smarts and skill to explain complicated, abstract ideas in a meaningful manner. This book does not do that. I wish it did!
At times cryptic, but nevertheless marvellous.......2000-06-02
This is the ONLY book I have seen which brings together all the many and various strands which are essential to the exciting new subjects arising currently around the question: What is Life? It is a stunning tour de force of the basic knowledge you need to possess to work in the areas of A-life or biological complexity.
I should warn: it's not a book I could read through in an afternoon, by any means. At times the descriptions are a little cryptic, so that I had to work at understanding what was being said. But the effort I had to put in was always rewarded with greater understanding. Thank you, Chris Adami.
Hard Science.......2000-05-10
Adami demonstrates how to use the tools of artificial life to conduct pure scientific research. A very clear and readable textbook on the subject, Adami makes me want to go back to graduate school. Here is a chance to take an introductory course in an exciting field of research that is truely table-top science. I loved the book and I didn't even use the CD and software that came with it.
An excellent textbook for this rapidly changing field........1998-08-24
Adami's book is the first comprehensive review of issues pertinent to the field of artificial life. The book is a textbook based on his lectures at CalTech. Some of the topics are a bit brief (Turing machines are summarized in four pages) but that is to be expected for a book whose goal is to integrate concepts from the fields of biology, chemistry, statistics, computer science, information science, etc. I found the book fascinating and Chris includes a CD-rom and several chapters on the Avida simulation developed at CalTech. There are numerous references and problems at the end of each chapter.
Book Description
Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability.
The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.
Customer Reviews:
Q-learner.......2007-02-19
I agree with reviewer Frank "Good introduction but not well structured, May 8, 2005" the authors are over-anxious to establish the credentials of RL in older research traditions. Much of the talk about optimal control for instance is confusing because this is a vast field and its assumed you know it. I found myself looking up some of the technical terms from other fields. In the end learning about these concepts didnt help my understanding. This is a pity because the concepts behind RL are relatively simple/
However in general I really enjoyed this book and this is the most accessible (while still being comprehensive) RL introduction out there.
Good introduction but not well structured.......2005-05-09
This book provides an easy to read introduction in reinforcement learning. It covers several approaches (dynamic programming, monte carlo, temproal differnce) and gives a lot of examples.
However, in my opinion it is neither well structured nor written. The book has no clear separation between theory and examples given to demonstrate the applications of the theory. Due to this, the theoretical ideas are blured instead of clearified. After going through the examples it is always possible to find out how it work, but this should not be necessary.
After reading this book you will definetely know the basics (even more) about reinforcement learning. However, I somehow expected more because of the names of the authors. Perhaps this is not only a problem of this book but of the field of reinforcement learning itself.
An excellent introduction.......2004-11-06
As a subfield of artificial intelligence, reinforcement learning has shown great success from both a theoretical and practical viewpoint. Taking the form of numerous applications in finance, network engineering, robot toys, and games, it is clear that his learning paradigm shows even greater promise for future developments. The authors summarize the foundations of reinforcement learning, some of this coming from their own work over the last decade.
The authors define reinforcement learning as learning how to map situations to actions so as to maximize a numerical reward. The machine that is indulging in reinforcement learning discovers on its own which actions will optimize the reward by trying out these actions. It is the ability of such a machine to learn from experience that distinguishes it from one that is indulging in supervised learning, for in the latter examples are needed to guide the machine to the proper concept or knowledge. The authors emphasize the "exploration-exploitation" tradeoffs that reinforcement-learning machines have to deal with as they interact with the environment.
For the authors, a reinforcement learning system consists of a `policy', a `reward function', a `value function', and a `model' of the environment. A policy is a mapping from the states of the environment that are perceived by the machine to the actions that are to be taken by the machine when in those states. The reward function maps each perceived state of the environment to a number (the reward). A value function specifies what is the good for the machine over the long run. A model, as the name implies, is a representation of the behavior of the environment. The authors emphasize that all of the reinforcement learning methods that are discussed in the book are concerned with the estimation of value functions, but they point out that other techniques are available for solving reinforcement learning problems, such as genetic algorithms and simulated annealing.
The authors use dynamic programming, Monte Carlo simulation, and temporal-difference learning to solve the reinforcement learning problem, but they emphasize that each of these methods will not give a free-lunch. An entire chapter is devoted to each of these methods however, giving the reader a good overview of the weaknesses and strengths of each of these approaches. The differences between them usual boil down to issues of performance rather than accuracy in the generated solutions. Temporal difference learning in fact is viewed in the book as a combination of Monte Carlo and dynamic programming techniques, and in the opinion of this reviewer, has resulted in some of the most impressive successes for applications based on reinforcement learning. One of these is TD-Gammon, developed to play backgammon, and which is also discussed in the book.
The authors emphasize that these three main strategies for solving reinforcement learning problems are not mutually exclusive. Instead each of them could be used simultaneously with the others, and they devote a few chapters in the book illustrating how this "unified" approach can be advantageous for reinforcement learning problems. They do this by using explicit algorithms and not just philosophical discussion. These discussions are very interesting and illustrate beautifully the idea that there is no "free lunch" in any of the different algorithms involved in reinforcement learning.
In the last chapter of the book the authors overview some of the more successful applications of reinforcement learning, one of them already mentioned. Another one discussed is the `acrobot', which is a two-link, underactuated robot, which models to some extent the motion of a gymnast on a high bar. The motion of the acrobot is to be controlled by swinging its tip above the first joint, with appropriate rewards given until this goal is reached. The authors use the `Sarsa' learning algorithm, developed earlier in the book, for solving this reinforcement learning problem. The acrobot is an example of the current intense interest in machine learning of physical motion and intelligent control theory.
Another example discussed in this chapter deals with the problem of elevator dispatching, which the authors include as an example of a problem that cannot be dealt with efficiently by dynamic programming. This problem is studied with Q-learning and via the use of a neural network trained by back propagation.
The authors also treat a problem of great importance in the cellular phone industry, namely that of dynamic channel allocation. This problem is formulated as a semi-Markov decision problem, and reinforcement learning techniques were used to minimize the probability of blocking a call. Reinforcement learning has become very important in the communications industry of late, as well as in queuing networks.
A Standard, Excellent Introductory Book.......2003-11-30
This book is undoubtedly the standard book on the topic of reinforcement learning by the two leading researchers in this field. Different from many other AI or maching learning books, this book presents not only the technical details of algorithms and methods, but also a uniquely unified view of how intelligent agents can improve by interacting with the environment. Besides, it is very readable, without much math or theory. The exercises are challenging and interesting, and will force you to understand the stuffs in the book!
Excellent introduction to reinforcement learning.......2003-08-03
I have this book more than a year now and I am going through it for the second time, so I think I have a pretty good picture about it.
The book consists of three parts. In the first part, "The Problem", the authors define the scope of issues reinfocement learning is dealing with and they give some interesting introductory examples. Then, they move on to the concept of evaluative feedback and, eventually, define the reinforcement learning problem formally.
The second part, "Elementary Solution Methods" consists of three more-less independent subparts: Dynamic Programming, Monte Carlo Methods and Temporal Difference Learning. All three fundamental reinforcement learning methods are presented in an interesting way and using good examples. Personally, I liked the TD-Learning part best and I agree that this method is indeed the central method and an original contribution of reinforecement learning to the field of machine learning.
The third part, "A Unified View" present more advanced techniques. The last chapter gives the most important case studies in reinforcement learning including Samuel's Checkers Player and Thesauro's TD-Gammon.
The book is very readable and every chapter ends with illustrative exercises (many of them actually are real programming projects!), always useful summary and very valuable bibliographical and historical remarks. Some subchapters are more advanced and therefore marked with '*'. I really recommend first two parts to any student ofd computer science or anyone interested in machine learning and fuzzy computing. The third part is much more advanced but it would be definitely interesting for advanced computer scientists and graduate students.
This is still the first edition of the book which means that the material is almost six years old, but it's the third printing, so there is lot of interest and I would suggest (for second edition) that authors include solutions to (at least selected) exercises, something like Knuth did in "The Art of Computer Programming".
Book Description
Emphasizing issues of computational efficiency, Michael Kearns and Umesh Vazirani introduce a number of central topics in computational learning theory for researchers and students in artificial intelligence, neural networks, theoretical computer science, and statistics.
Computational learning theory is a new and rapidly expanding area of research that examines formal models of induction with the goals of discovering the common methods underlying efficient learning algorithms and identifying the computational impediments to learning.
Each topic in the book has been chosen to elucidate a general principle, which is explored in a precise formal setting. Intuition has been emphasized in the presentation to make the material accessible to the nontheoretician while still providing precise arguments for the specialist. This balance is the result of new proofs of established theorems, and new presentations of the standard proofs.
The topics covered include the motivation, definitions, and fundamental results, both positive and negative, for the widely studied L. G. Valiant model of Probably Approximately Correct Learning; Occam's Razor, which formalizes a relationship between learning and data compression; the Vapnik-Chervonenkis dimension; the equivalence of weak and strong learning; efficient learning in the presence of noise by the method of statistical queries; relationships between learning and cryptography, and the resulting computational limitations on efficient learning; reducibility between learning problems; and algorithms for learning finite automata from active experimentation.
Customer Reviews:
This is interesting stuff.......2000-11-18
Kearns is an impressive researcher, precise and succinct. The material on this book follows a tradition of careful proofs of fundamental issues in learning. I wouldn't think this is material of practical use; for that kind of material I'd recommend the new edition of Duda. Rather, Kearns is one of a team of researchers pushing the frontier of proving what is learnable and what is not, why some representations are good for learning and which are not, the dimensionality of the target problem (related to overfitting) working with prinpled definitions of what it is meant to learn borrowed from computational complexity theory.
Books:
- Introduction to Transportation Engineering
- Kendall's Advanced Theory of Statistics: Volume 2B: Bayesian Inference (Arnold Publication)
- Lasers and Optical Fibers in Medicine (Physical Techniques in Biology and Medicine)
- Little, Brown Essential Handbook, The (5th Edition)
- Many-Particle Physics (Physics of Solids and Liquids)
- Markov Decision Processes: Discrete Stochastic Dynamic Programming (Wiley Series in Probability and Statistics)
- Mathematical Methods of Classical Mechanics (Graduate Texts in Mathematics)
- Medical Firsts: From Hippocrates to the Human Genome
- Men's Health: The Book of Muscle--The World's Most Authoritative Guide to Building Your Body
- Modern Communications Jamming Principles and Techniques (The Artech House Information Warfare Library)
Books Index
Books Home
Recommended Books
- Sustainable Construction: Green Building Design and Delivery
- Lessons with Lendon: 25 Progressive Dressage Lessons Take You from Basic "Whoa and Go" to Your First
- French Modern: Art Deco Graphic Design
- History of Vatican II: The Mature Council - 2nd Period and Intersession, A Mature Council, October 1
- Marching to the Drums: Eyewitness Accounts of War from the Charge of the Light Brigade to the Siege
- My Brother's Road: An American's Fateful Journey to Armenia
- Mind and Nature: A Necessary Unity
- Time and Information Management That Really Works!: Organization for the '90s
- Global Capitalism at Bay
- European Marketing Forecasts 2004/2005
Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems
Biophysics of Computation: Information Processing in Single Neurons (Computational Neuroscience)
Spikes: Exploring the Neural Code (Computational Neuroscience)
Neural Networks for Pattern Recognition
Information Theory, Inference & Learning Algorithms
