Product Description

The popularity of artificial intelligence continues to grow as more and more uses are found for the technology. AI Application Programming Second Edition is completely updated to supply both the conceptual background and the real-world examples needed to begin using AI in software projects. Each technology is illustrated with a model implementation and application, and complete source code for each example is provided on the companion CD-ROM. Selected applications cover data mining, genetic algorithms, game programming, embedded rules-based engines, and the World Wide Web.

KEY FEATURES:
* Covers cutting-edge AI concepts such as neural networks, natural language processing, intelligent agents, genetic algorithms, rule-based systems, unsupervised learning algorithms, migratory software, and more
* Teaches each AI concept through a practical application, including a financial data miner, a Web spider, a networked data collector, a game program, an embedded battery charger control system, an embedded rules-based engine for log monitoring, and a fault tolerance subsystem
* Groups AI topics by conceptual subfields (machine learning, evolutionary methods, symbolic methods) for better "big picture" understanding and more focused specialization
* Provides a background in the history of AI, the distinct branches of this broad field, and the philosophical underpinnings and issues associated with these technologies
* Includes a CD-ROM (Win/Linux) with complete, fully commented source code in C for every application in the book
* Exercise sets for each chapter are located in Appendix A for use as a Textbook

Product Details

• Amazon Sales Rank: #569285 in Books
• Published on: 2005-06-03
• Released on: 2005-06-03
• Original language: English
• Number of items: 1
• Binding: Paperback
• 473 pages

Features

• ISBN13: 9781584504214
• Condition: NEW
• Notes: Brand New from Publisher. No Remainder Mark.
• Click here to view our Condition Guide and Shipping Prices

About the Author
M. Tim Jones has been developing software since 1986. He has published articles on embedded systems, network protocols, and artificial intelligence for Dr. Dobb's Journal, Embedded Systems Programming, and Embedded Linux Journal. In addition, he is the author of GNU/Linux Application Programming and TCP/IP Application Layer Protocols for Embedded Systems. He resides in Longmont, CO, where he works as a Senior Principal Software Engineer.

Customer Reviews

Great, in depth, recursively precise!
I enjoyed working through this text, but not without some re-visiting of my calculus classes and trigonometry brush-ups.
All in all a very good book, and also a great Graduate level reference for the inner workings of actual Artificial Intelligence algorithms.
If you are well prepared, this book is to the point, and well worth the read. Prepare for a visit to College-level Physics theorems, as many algorithms given require a working knowledge of the advanced principles of the science.

Hope this helps-

The book has its values, but also got serious problems
Most of other reviewer think highly of this book. I also agree, to a certain extent, that the book's is valuable and fill in the gap between "talks" and "walks".

However, there are two things I have to point out: One, the editing/basic correctness check of this book is kinda terrible. For example, P72 on Particle Swarm Optimization, the 4.2 formula is obviously WRONG and not consistent with the rest of discussion. Also on P74, the position vector calculation is wrong as well: it also seems the author/editor cut & copy two blocks of text.

Second, I don't like is the lack of explaination on certain important notations and equations, which is very important to be at least "self-contained" for such a "cover everything" book. For example, P210 on reinforcement learning, Equation 9.2 has a general explaination of what it is, but non of those notation/symbols in the equation make sense in the context.

So, in general, be aware its pro and cons.

Great second edition of an applied book on AI
Scientists started the field of AI research in the 1950's with the now largely failed quest to produce machines that think. However, they did open the door to making improved individual products that can "learn" how to do their limited jobs better, and they also opened the door to the use of AI in games and in recommender systems such as you see here on Amazon.
This book is the second edition of the successful book by Tim Jones on different facets of AI, how they can be used, and how to write programs that implement the necessary algorithms. The book begins with a short but insightful chapter on the history of AI, followed by a series of chapters, each covering a specific AI technique. The last chapter covers the state of AI today. Each chapter begins with a short description of the technique covered, sometimes including parallels to the real world that are behind the algorithmic choices of the technique. Next, the algorithm is described, and a sample implementation is given and discussed. Last, the author presents examples of problems that can be solved by the given technique. This book basically replaces the first edition, as everything in that book is in this one plus the A* pathfinding algorithm, particle swarm optimization, classifier systems, reinforcement learning, and natural language processing. For several of the techniques variations and tuning opportunities are presented, allowing the reader/programmer to easily adapt the technique to a different problem of a similar type. There are also plenty of illustrations and diagrams, making the material easier to absorb. I highly recommend that you purchase this second edition, even if you already have the first edition. It is a worthwhile upgrade. The author assumes that the reader has already been exposed to the basic ideas of artificial intelligence and is proficient at programming in C. I notice that Amazon does not show the table of contents for the 2nd edition, so I do that here.
1. History of AI
2. Pathfind and the A-Star Algorithm **
3. Simulated Annealing
4. Particle Swarm Optimization **
5. Introduction to Adaptive Resonance Theory (ART1)
6. Classifier Systems **
7. Ant Algorithms
8. Introduction to Neural Networks and the BackPropagation Algorithm
9. Introduction to Reinforcement Learning **
10. Introduction to Genetic Algorithms
11. Artificial Life
12. Introduction to Rules-Based Systems
13. Introduction to Fuzzy Logic
14. Natural Language Processing **
15. The Bigram Model
16. Agent-Based Software
17. AI Today
** Denotes a totally new chapter