Verkauf durch Sack Fachmedien

Neapolitan

Contemporary Artificial Intelligence

Medium: Buch
ISBN: 978-1-4398-4469-4
Verlag: CRC Press
Erscheinungstermin: 14.08.2012
Nicht mehr lieferbar

The notion of artificial intelligence (AI) often sparks thoughts of characters from science fiction, such as the Terminator and HAL 9000. While these two artificial entities do not exist, the algorithms of AI have been able to address many real issues, from performing medical diagnoses to navigating difficult terrain to monitoring possible failures of spacecrafts. Exploring these algorithms and applications, Contemporary Artificial Intelligence presents strong AI methods and algorithms for solving challenging problems involving systems that behave intelligently in specialized domains such as medical and software diagnostics, financial decision making, speech and text recognition, genetic analysis, and more.

One of the first AI texts accessible to students, the book focuses on the most useful problem-solving strategies that have emerged from AI. In a student-friendly way, the authors cover logic-based methods; probability-based methods; emergent intelligence, including evolutionary computation and swarm intelligence; data-derived logical and probabilistic learning models; and natural language understanding. Through reading this book, students discover the importance of AI techniques in computer science.


Produkteigenschaften


Autoren/Hrsg.

Autoren

Introduction to Artificial Intelligence
History of Artificial Intelligence
Contemporary Artificial Intelligence

LOGICAL INTELLIGENCE
Propositional Logic
Basics of Propositional Logic
Resolution
Artificial Intelligence Applications
Discussion and Further Reading

First-Order Logic
Basics of First-Order Logic
Artificial Intelligence Applications
Discussion and Further Reading

Certain Knowledge Representation
Taxonomic Knowledge
Frames
Nonmonotonic Logic
Discussion and Further Reading

PROBABILISTIC INTELLIGENCE
Probability
Probability Basics
Random Variables
Meaning of Probability
Random Variables in Applications

Probability in the Wumpus World

Uncertain Knowledge Representation
Intuitive Introduction to Bayesian Networks
Properties of Bayesian Networks
Causal Networks as Bayesian Networks
Inference in Bayesian Networks
Networks with Continuous Variables
Obtaining the Probabilities
Large-Scale Application: Promedas

Advanced Properties of Bayesian Network

Entailed Conditional Independencies

Faithfulness

Markov Equivalence

Markov Blankets and Boundaries

Decision Analysis

Decision Trees

Influence Diagrams

Modeling Risk Preferences

Analyzing Risk Directly

Good Decision versus Good Outcome

Sensitivity Analysis

Value of Information
Discussion and Further Reading

EMERGENT INTELLIGENCE
Evolutionary Computation
Genetics Review

Genetic Algorithms
Genetic Programming
Discussion and Further Reading

Swarm Intelligence

Ant System

Flocks

Discussion and Further Reading

LEARNING
Learning Deterministic Models

Supervised Learning

Regression
Learning a Decision Tree

Learning Probabilistic Model Parameters

Learning a Single Parameter

Learning Parameters in a Bayesian Network

Learning Parameters with Missing Data

Learning Probabilistic Model Structure

Structure Learning Problem

Score-Based Structure Learning
Constraint-Based Structure Learning
Application: MENTOR
Software Packages for Learning

Causal Learning
Class Probability Trees
Discussion and Further Reading

More Learning

Unsupervised Learning

Reinforcement Learning

Discussion and Further Reading

LANGUAGE UNDERSTANDING
Natural Language Understanding

Parsing
Semantic Interpretation

Concept/Knowledge Interpretation

Information Extraction

Discussion and Further Reading

Bibliography

Index