Zur Startseite gehen
0,00 €*
Cover: 9783642060526 | Universal Artificial Intelligence | Marcus Hutter | Taschenbuch | 2010
Dekorationsartikel gehören nicht zum Leistungsumfang.
Universal Artificial Intelligence
Sequential Decisions Based on Algorithmic Probability
Taschenbuch von Marcus Hutter
Sprache: Englisch

85,30 €*

inkl. MwSt.

Versandkostenfrei per Post / DHL

Lieferzeit 4-7 Werktage

Kategorien:
Beschreibung
Personal motivation. The dream of creating artificial devices that reach or outperform human inteUigence is an old one. It is also one of the dreams of my youth, which have never left me. What makes this challenge so interesting? A solution would have enormous implications on our society, and there are reasons to believe that the AI problem can be solved in my expected lifetime. So, it's worth sticking to it for a lifetime, even if it takes 30 years or so to reap the benefits. The AI problem. The science of artificial intelligence (AI) may be defined as the construction of intelligent systems and their analysis. A natural definition of a system is anything that has an input and an output stream. Intelligence is more complicated. It can have many faces like creativity, solving prob­ lems, pattern recognition, classification, learning, induction, deduction, build­ ing analogies, optimization, surviving in an environment, language processing, and knowledge. A formal definition incorporating every aspect of intelligence, however, seems difficult. Most, if not all known facets of intelligence can be formulated as goal driven or, more precisely, as maximizing some utility func­ tion. It is, therefore, sufficient to study goal-driven AI; e. g. the (biological) goal of animals and humans is to survive and spread. The goal of AI systems should be to be useful to humans.
Personal motivation. The dream of creating artificial devices that reach or outperform human inteUigence is an old one. It is also one of the dreams of my youth, which have never left me. What makes this challenge so interesting? A solution would have enormous implications on our society, and there are reasons to believe that the AI problem can be solved in my expected lifetime. So, it's worth sticking to it for a lifetime, even if it takes 30 years or so to reap the benefits. The AI problem. The science of artificial intelligence (AI) may be defined as the construction of intelligent systems and their analysis. A natural definition of a system is anything that has an input and an output stream. Intelligence is more complicated. It can have many faces like creativity, solving prob­ lems, pattern recognition, classification, learning, induction, deduction, build­ ing analogies, optimization, surviving in an environment, language processing, and knowledge. A formal definition incorporating every aspect of intelligence, however, seems difficult. Most, if not all known facets of intelligence can be formulated as goal driven or, more precisely, as maximizing some utility func­ tion. It is, therefore, sufficient to study goal-driven AI; e. g. the (biological) goal of animals and humans is to survive and spread. The goal of AI systems should be to be useful to humans.
Über den Autor

Marcus Hutter received his masters in computer sciences in 1992 at the Technical University in Munich, Germany. After his PhD in theoretical particle physics he developed algorithms in a medical software company for 5 years. For four years he has been working as a researcher at the AI institute IDSIA in Lugano, Switzerland. His current interests are centered around reinforcement learning, algorithmic information theory and statistics, universal induction schemes, adaptive control theory, and related areas.

IDSIA (Istituto Dalle Molle di Studi sull'Intelligenza Artificiale) is a non-profit oriented research institute for artificial intelligence, affiliated with both the University of Lugano and SUPSI. It focusses on machine learning (artificial neural networks, reinforcement learning), optimal universal artificial intelligence and optimal rational agents, operations research, complexity theory, and robotics. In Business Week's "X-Lab Survey" IDSIA was ranked in fourth place in the category "Computer Science - Biologically Inspired", after much larger institutions. IDSIA also ranked in the top 10 of the broader category "Artificial Intelligence."

Zusammenfassung
This book presents sequential decision theory from a novel algorithmic information theory perspective. While the former is suited for active agents in known environment, the latter is suited for passive prediction in unknown environment. The book introduces these two different ideas and removes the limitations by unifying them to one parameter-free theory of an optimal reinforcement learning agent embedded in an unknown environment. Most AI problems can easily be formulated within this theory, reducing the conceptual problems to pure computational ones. Considered problem classes include sequence prediction, strategic games, function minimization, reinforcement and supervised learning. The discussion includes formal definitions of intelligence order relations, the horizon problem and relations to other approaches.
Inhaltsverzeichnis
Short Tour Through the Book.- Simplicity & Uncertainty.- Universal Sequence Prediction.- Agents in Known Probabilistics Environments.- The Universal Algorithmic Agent AIXI.- Important Environmental Classes.- Computational Aspects.- Discussion.
Details
Erscheinungsjahr: 2010
Genre: Informatik
Rubrik: Naturwissenschaften & Technik
Medium: Taschenbuch
Seiten: 304
Reihe: Texts in Theoretical Computer Science. An EATCS Series
Inhalt: xx
278 S.
ISBN-13: 9783642060526
ISBN-10: 3642060528
Sprache: Englisch
Ausstattung / Beilage: Paperback
Einband: Kartoniert / Broschiert
Autor: Hutter, Marcus
Auflage: Softcover reprint of hardcover 1st ed. 2005
Hersteller: Springer Berlin
Springer Berlin Heidelberg
Texts in Theoretical Computer Science. An EATCS Series
Maße: 235 x 155 x 17 mm
Von/Mit: Marcus Hutter
Erscheinungsdatum: 06.11.2010
Gewicht: 0,464 kg
preigu-id: 107117077
Über den Autor

Marcus Hutter received his masters in computer sciences in 1992 at the Technical University in Munich, Germany. After his PhD in theoretical particle physics he developed algorithms in a medical software company for 5 years. For four years he has been working as a researcher at the AI institute IDSIA in Lugano, Switzerland. His current interests are centered around reinforcement learning, algorithmic information theory and statistics, universal induction schemes, adaptive control theory, and related areas.

IDSIA (Istituto Dalle Molle di Studi sull'Intelligenza Artificiale) is a non-profit oriented research institute for artificial intelligence, affiliated with both the University of Lugano and SUPSI. It focusses on machine learning (artificial neural networks, reinforcement learning), optimal universal artificial intelligence and optimal rational agents, operations research, complexity theory, and robotics. In Business Week's "X-Lab Survey" IDSIA was ranked in fourth place in the category "Computer Science - Biologically Inspired", after much larger institutions. IDSIA also ranked in the top 10 of the broader category "Artificial Intelligence."

Zusammenfassung
This book presents sequential decision theory from a novel algorithmic information theory perspective. While the former is suited for active agents in known environment, the latter is suited for passive prediction in unknown environment. The book introduces these two different ideas and removes the limitations by unifying them to one parameter-free theory of an optimal reinforcement learning agent embedded in an unknown environment. Most AI problems can easily be formulated within this theory, reducing the conceptual problems to pure computational ones. Considered problem classes include sequence prediction, strategic games, function minimization, reinforcement and supervised learning. The discussion includes formal definitions of intelligence order relations, the horizon problem and relations to other approaches.
Inhaltsverzeichnis
Short Tour Through the Book.- Simplicity & Uncertainty.- Universal Sequence Prediction.- Agents in Known Probabilistics Environments.- The Universal Algorithmic Agent AIXI.- Important Environmental Classes.- Computational Aspects.- Discussion.
Details
Erscheinungsjahr: 2010
Genre: Informatik
Rubrik: Naturwissenschaften & Technik
Medium: Taschenbuch
Seiten: 304
Reihe: Texts in Theoretical Computer Science. An EATCS Series
Inhalt: xx
278 S.
ISBN-13: 9783642060526
ISBN-10: 3642060528
Sprache: Englisch
Ausstattung / Beilage: Paperback
Einband: Kartoniert / Broschiert
Autor: Hutter, Marcus
Auflage: Softcover reprint of hardcover 1st ed. 2005
Hersteller: Springer Berlin
Springer Berlin Heidelberg
Texts in Theoretical Computer Science. An EATCS Series
Maße: 235 x 155 x 17 mm
Von/Mit: Marcus Hutter
Erscheinungsdatum: 06.11.2010
Gewicht: 0,464 kg
preigu-id: 107117077
Warnhinweis

Ähnliche Produkte

Ähnliche Produkte

Taschenbuch
Cover: 9780715647332 | How to Create a Mind | The Secret of Human Thought Revealed | Kurzweil
How to Create a Mind
The Secret of Human Thought Revealed
EAN: 9780715647332
Sprache: Englisch
Von/Mit: Ray Kurzweil

13,85 €*

Lieferzeit 1-2 Werktage

Taschenbuch
Cover: 9780486445281 | Techniques and Applications of Path Integration | L. S. Schulman
Techniques and Applications of Path Integration
EAN: 9780486445281
Sprache: Englisch
Von/Mit: L. S. Schulman

26,35 €*

Lieferzeit 1-2 Wochen

Taschenbuch
Cover: 9783319514567 | Quantum Spin Systems on Infinite Lattices | A Concise Introduction
Quantum Spin Systems on Infinite Lattices
A Concise Introduction
EAN: 9783319514567
Sprache: Englisch
Von/Mit: Pieter Naaijkens

41,75 €*

Lieferzeit 4-7 Werktage

Taschenbuch
Cover: 9783662603413 | Statistik für Wirtschaftswissenschaftler | Albrecht Ungerer (u. a.)
Statistik für Wirtschaftswissenschaftler
Eine anwendungsorientierte Darstellung
EAN: 9783662603413
Sprache: Deutsch
Von/Mit: Albrecht Ungerer (u. a.)

32,99 €*

Lieferzeit 4-7 Werktage

Taschenbuch
Cover: 9781492094340 | Advancing into Analytics | From Excel to Python and R | George Mount
Advancing Into Analytics
From Excel to Python and R
EAN: 9781492094340
Sprache: Englisch
Von/Mit: George Mount

58,90 €*

Lieferzeit 1-2 Wochen

Taschenbuch
Cover: 9781789139624 | Voicebot and Chatbot Design | Rachel Batish | Taschenbuch | Paperback
Voicebot and Chatbot Design
EAN: 9781789139624
Sprache: Englisch
Von/Mit: Rachel Batish

51,25 €*

Lieferzeit 4-7 Werktage

Buch
Cover: 9780997316001 | Computer Science Distilled | Wladston Ferreira Filho | Buch | Englisch
Computer Science Distilled
Learn the Art of Solving Computational Problems
EAN: 9780997316001
Sprache: Englisch
Von/Mit: Wladston Ferreira Filho

59,40 €*

Lieferzeit 2-3 Wochen

Taschenbuch
Cover: 9781803234151 | Learn Blender Simulations the Right Way | Stephen Pearson | Buch
Learn Blender Simulations the Right Way
Create attractive and realistic animations with Mantaflow, rigid and soft bodies, and Dynamic Paint
EAN: 9781803234151
Sprache: Englisch
Von/Mit: Stephen Pearson

81,65 €*

Lieferzeit 4-7 Werktage

Taschenbuch
Cover: 9781032234953 | Model-Based Clustering, Classification, and Density Estimation...
Model-Based Clustering, Classification, and Density Estimation Using mclust in R
EAN: 9781032234953
Von/Mit: Adrian E. Raftery (u. a.)

67,00 €*

Aktuell nicht verfügbar

Taschenbuch
Cover: 9783031137167 | Design of Heuristic Algorithms for Hard Optimization | Taillard | Buch
Design of Heuristic Algorithms for Hard Optimization
With Python Codes for the Travelling Salesman Problem
EAN: 9783031137167
Sprache: Englisch
Von/Mit: Éric D. Taillard

36,15 €*

Lieferzeit 4-7 Werktage

Taschenbuch
Cover: 9783031059230 | Scheduling | Theory, Algorithms, and Systems | Michael L. Pinedo
Scheduling
Theory, Algorithms, and Systems
EAN: 9783031059230
Sprache: Englisch
Von/Mit: Michael L. Pinedo

56,95 €*

Lieferzeit 4-7 Werktage

Diese Website verwendet Cookies, um eine bestmögliche Erfahrung bieten zu können. Mehr Informationen ...