nach oben

2016 | Buch

Introduction to Artificial Intelligence

verfasst von: Mariusz Flasiński

Verlag: Springer International Publishing

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

In the chapters in Part I of this textbook the author introduces the fundamental ideas of artificial intelligence and computational intelligence. In Part II he explains key AI methods such as search, evolutionary computing, logic-based reasoning, knowledge representation, rule-based systems, pattern recognition, neural networks, and cognitive architectures. Finally, in Part III, he expands the context to discuss theories of intelligence in philosophy and psychology, key applications of AI systems, and the likely future of artificial intelligence. A key feature of the author's approach is historical and biographical footnotes, stressing the multidisciplinary character of the field and its pioneers.

The book is appropriate for advanced undergraduate and graduate courses in computer science, engineering, and other applied sciences, and the appendices offer short formal, mathematical models and notes to support the reader.

Inhaltsverzeichnis

Frontmatter

Fundamental Ideas of Artificial Intelligence

Frontmatter

Chapter 1. History of Artificial Intelligence

Abstract

Many fundamental methodological issues of Artificial Intelligence have been of great importance in philosophy since ancient times. Such philosophers as Aristotle, St. Thomas Aquinas, William of Ockham, René Descartes, Thomas Hobbes, and Gottfried W. Leibniz have asked the questions: “What are basic cognitive operations?”, “What necessary conditions should a (formal) language fulfill in order to be an adequate tool for describing the world in a precise and unambiguous way?”, “Can reasoning be automatized?”.

Mariusz Flasiński

Chapter 2. Symbolic Artificial Intelligence

Abstract

Basic methodological assumptions of methods which belong to symbolic Artificial Intelligence are presented in this chapter.

Mariusz Flasiński

Chapter 3. Computational Intelligence

Abstract

Computational Intelligence, CI, is the second group of methods in Artificial Intelligence. It is a complementary approach with respect to symbolic AI.

Mariusz Flasiński

Artificial Intelligence Methods

Frontmatter

Chapter 4. Search Methods

Abstract

We begin our presentation of AI models with search methods not only for chronological reasons, but also because of their methodological versatility.

Mariusz Flasiński

Chapter 5. Evolutionary Computing

Abstract

Evolutionary computing is the most important group of methods within the biology-inspired approach, because of their well-developed theoretical foundations as well as the variety of their practical applications.

Mariusz Flasiński

Chapter 6. Logic-Based Reasoning

Abstract

Two models of problem solving which are based on logic, reasoning as theorem proving and reasoning as symbolic computation, are discussed in this chapter. Both models are implemented in AI systems with the help of the declarative programming paradigm, which has been introduced in Sect. 2.2.

Mariusz Flasiński

Chapter 7. Structural Models of Knowledge Representation

Abstract

Constructing so-called ontologies (Although there is an analogy between the notion of ontology in computer science and the notion of ontology in philosophy, we should differentiate between the two notions. In philosophy ontology is the study of being, its essential properties and its ultimate reasons.) is one of the main goals of applying structural models of knowledge representation, which have been introduced in Sect. 2.4. In Artificial Intelligence and in computer science, an ontology (The system Cyc, which is developed by D. Lenat, is one of the biggest AI systems based on an ontology-based approach.) is defined as a formal specification (conceptualization) of a certain (application) domain which is defined in such a way that it can be used for solving various problems (in the scope of this domain) with the help of general reasoning methods (Such standard reasoning methods are analogous to a universal reasoning scheme, which is discussed in a previous chapter.). Such a specification is of the structural form. It can be treated as a kind of encyclopedia for the domain which contains descriptions of notions, objects, relations between them, etc.

Mariusz Flasiński

Chapter 8. Syntactic Pattern Analysis

Abstract

In syntactic pattern analysis, also called syntactic pattern recognition [97, 104], reasoning is performed on the basis of structural representations which describe things and phenomena belonging to the world. A set of such structural representations, called (structural) patterns, constitutes the database of an AI system.

Mariusz Flasiński

Chapter 9. Rule-Based Systems

Abstract

The main idea of reasoning in rule-based systems is, in fact, the same as in the case of logic-based reasoning introduced in Chap. 6. Both models are based on deductive reasoning.

Mariusz Flasiński

Chapter 10. Pattern Recognition and Cluster Analysis

Abstract

Let us begin with a terminological remark, which concerns the notion of a pattern. In pattern recognition and cluster analysis various objects, phenomena, processes, structures, etc. can be considered as patterns.

Mariusz Flasiński

Chapter 11. Neural Networks

Abstract

As we have mentioned in the previous chapter, the neural network model (NN) is sometimes treated as one of the three approaches to pattern recognition (along with the approach introduced in the previous chapter and syntactic-structural pattern recognition).

Mariusz Flasiński

Chapter 12. Reasoning with Imperfect Knowledge

Abstract

If we reason about propositions in AI systems which are based on classic logic, we use only two possible logic values, i.e., true and false. However, in the case of reasoning about the real (physical) world such a two-valued evaluation is inadequate, because of the aspect of uncertainty

Mariusz Flasiński

Chapter 13. Defining Vague Notions in Knowledge-Based Systems

Abstract

The second reason for the unreliability of inference in AI systems, apart from imperfection of knowledge, is imperfection of the system of notions which is used for a description of the real (physical) world.

Mariusz Flasiński

Chapter 14. Cognitive Architectures

Abstract

In this part of the monograph we present various methods used for problem solving by artificial intelligence systems. This chapter, however, does not include a description of any method, but it contains a discussion on the possible structure of an artificial intelligence system.

Mariusz Flasiński

Selected Issues in Artificial Intelligence

Frontmatter

Chapter 15. Theories of Intelligence in Philosophy and Psychology

Abstract

Basic approaches to the simulation of sensual/intellectual cognitive abilities, such as problem solving, pattern recognition, constructing knowledge representations, learning, etc. have been presented in previous parts of the book.

Mariusz Flasiński

Chapter 16. Application Areas of AI Systems

Abstract

Before we discuss the issue of the possibility of constructing an intelligent artificial system in the last chapter, we now summarize practical results concerning application areas of AI systems.

Mariusz Flasiński

Chapter 17. Prospects of Artificial Intelligence

Abstract

In Chap. 15 philosophical (epistemological) approaches to issues of mind, cognition, knowledge, and human intelligence have been presented. In the first section of this chapter contemporary views concerning the essence of artificial intelligence are discussed. As one can easily notice these views result from epistemological assumptions.

Mariusz Flasiński

Backmatter

Titel: Introduction to Artificial Intelligence
verfasst von: Mariusz Flasiński
Verlag: Springer International Publishing
Electronic ISBN: 978-3-319-40022-8
Print ISBN: 978-3-319-40020-4
DOI: https://doi.org/10.1007/978-3-319-40022-8