The Handbook of Artificial Intelligence: Volume 1 by Avron Barr (PDF)

Description

The Handbook of Artificial Intelligence, Volume I focuses on the progress in artificial intelligence (AI) and its increasing applications, including parsing, grammars, and search methods.The book first elaborates on AI, AI handbook and literature, problem representation, search methods, and sample search programs. The text then ponders on representation of knowledge, including survey of representation techniques and representation schemes. The manuscript explores understanding natural languages, as well as machine translation, grammars, parsing, test generation, and natural language processing systems. The book also takes a look at understanding spoken language, including systems architecture and the ARPA SUR projects. The text is a valuable source of information for computer science experts and researchers interested in pursuing further research in artificial intelligence.

User’s Reviews

Reviews from Amazon users which were colected at the time this book was published on the website:

⭐I was pleasantly surprised by the thoroughness with which the author treated the subject of AI. The various subtopics that make up the whole field are explained clearly. Examples abound and references for further research are included throughout the text. The author is apparently passionate about the subject, and has made it easy for me to see that he knows what makes the field of AI, as it was known then and is now, work. I really appreciate the author starting the core of the treatise with the topic of Search, one of the major areas of work and applications in the field of AI.The writing was clear and concise, except at parts like an attempt to explain the meaning of heuristic. The author makes the point that there is no clear and definite meaning to the term by showing that he was not trying to give a clear definition to the device called heuristics. In other words the style of writing goes beyond English, to teaching with experience and example. A kind of immersion, though it be into temporary confusion. When a topic, like heuristics, which is confused in practice, is explained, the author helped me to understand that, and to even feel the confusion to some degree. Do not get me wrong here, most of the book was very well written and clear. I will use it often in my AI research and development, and I am sure that I will be able to use it to help me fix whatever problems I might find in AI products that are being used today. That was my primary reason for buying this book; to help me to work and develop and even invent in the field of AI. I was not disappointed .This handbook will provide me with the right information, and thus do much to enable successful R&D for me. Written like the mixture of a reference book and a textbook, it can be used in either way. There were no exercises or problems at the end of sections, but thought experiments and problem descriptions followed by solutions are occurring often in the Handbook. Thus the reader is made to learn, practice, and think about the subject of Artificial Intelligence.

⭐This is the first volume of a 3-volume set published in the early 1980’s and thus could be thought of as a summary of what was known at the time in the field of artificial intelligence (A.I.). Now sometimes referred to as “GOFAI” for “good ole-fashioned artificial intelligence”, this set of books can still be referred to profitably by anyone curious about the applications of artificial intelligence. Indeed, many of the algorithms discussed in this volume are still being used, and very robustly, in current implementations of artificial intelligence. A lot has happened since this volume was published, especially in the area of chess playing and logic programming, but there are many sections of the book that are still up-to-date. After a brief introduction to A.I. in chapter one, chapter two overviews the use of search algorithms for intelligent problem solving. The emphasis initially is on the problem representations that form the basis of search techniques, such as state-space and problem-reduction representations. Game tree representations are also discussed. The algorithms that implement the problem representations are then treated. If the search space is viewed merely syntactically, these are called “blind search” algorithms, which are distinguished from “heuristic” methods, which exploit various structural information about the problem in order to limit the search. Examples of blind search methods that are discussed include breadth-first, uniform-cost, depth-first, and bidirectional search. Examples of heuristic methods discussed are ordered state-space, bidirectional, and the famous A*-algorithm, the latter of which is still finding considerable use in new applications of A.I. Examples of game tree search that are covered include the minimax procedure, the negmax formalism, and alpha-beta pruning. There is discussion on the use of heuristics in game tree search, but this part is out-of-date due to the advances made in chess playing, checkers, etc, since this volume was published. Chapter three is an overview of knowledge representation in A.I. The author takes a pragmatic approach to the nature of knowledge and intelligence, and defines the “representation of knowledge” as a combination of data structures and interpretive procedures that will lead to what he calls “knowledgeable” behavior. A book needs a reader before it could be considered knowledge, argues the author. He calls this whole enterprise “experimental epistemology” , which endeavors to create programs that exhibit intelligent behavior. The chapter gives an overview of the knowledge representation schemes used in A.I. and discusses their uses and shortcomings. Also, the tension between the advocates of declarative versus procedural knowledge representations is discussed. Declarative systems are more logical/mathematically based, and were exemplified by theorem-provers based on logical resolution. The procedural approach emphasized a more directed approach to the problem of inference and one that makes the reasoning process more understandable. There is a brief discussion on semantic nets, which were invented as a model of human associative memory. The net consists of nodes, which represent concepts, objects, or events, and links between the nodes. The relevant facts about a concept can be inferred from the nodes to which they are linked directly, and so an extensive database search is not necessary. The semantics of net structures depends only on the program that uses them, and so any notion of “logical validity” of inferences from using the net is absent. Production systems are also discussed in this chapter, these being developed as models of human cognition. These systems are called “modular” knowledge representation schemes in that the database consists of rules, or “productions”, that take the form of condition-action pairs. The conditions in which each rule is applicable are made explicit and thus the interactions between the rules are minimized. These systems have been used to control the interaction between declarative and procedural statements and to develop autonomous learning systems. In addition, the chapter includes a discussion of the “frame” knowledge representation system, which at the time of publication, was just getting started in A.I. research. It has been widely discussed since then, mostly in the context of studying how to implement reasoning about actions, and became to be known as the “frame problem”. The proliferation of the frame axioms needed made reasoning about actions difficult or cumbersome, but was later solved using what are now called “successor-state axioms”. The chapter also includes a discussion of the standard logical representational schemes: propositional and first-order predicate logic. Since the time of publication, and due to the interest in developing “common-sense” reasoning machines, second-order predicate logic has made its appearance in A.I. research, sometimes being called “ontological engineering” in the literature. Also, due to the time of publication, there is no discussion of inductive logic programming, which has recently gained importance in A.I. research and its applications. Chapter four covers the very important topic of natural language understanding. This is one of the areas in A.I. that has been the target of an enormous amount of research, for the ability of a computer to converse with a human fluently and with understanding would be a major advance for A.I., perhaps even an “acid test” that true intelligence has finally been achieved in a machine. The chapter gives a brief history of research in natural language processing and discusses the early attempts at machine translation from one language to another. There is also extensive discussion on grammars, parsing techniques, and text generation. Several examples of programs used for natural language processing that were popular at the time of publication are discussed.

Keywords

Free Download The Handbook of Artificial Intelligence: Volume 1 in PDF format
The Handbook of Artificial Intelligence: Volume 1 PDF Free Download
Download The Handbook of Artificial Intelligence: Volume 1 2014 PDF Free
The Handbook of Artificial Intelligence: Volume 1 2014 PDF Free Download
Download The Handbook of Artificial Intelligence: Volume 1 PDF
Free Download Ebook The Handbook of Artificial Intelligence: Volume 1