Soft Computing and Human-Centered Machines (häftad)
Fler böcker inom
Format
Häftad (Paperback / softback)
Språk
Engelska
Antal sidor
327
Utgivningsdatum
2013-10-03
Upplaga
Softcover reprint of the original 1st ed. 2000
Förlag
Springer Verlag, Japan
Medarbetare
Liu, Z. -Q. (ed.), Miyamoto, S. (ed.)
Illustrationer
9 Illustrations, black and white; XVIII, 327 p. 9 illus.
Dimensioner
234 x 156 x 19 mm
Vikt
490 g
Antal komponenter
1
Komponenter
1 Paperback / softback
ISBN
9784431679868
Soft Computing and Human-Centered Machines (häftad)

Soft Computing and Human-Centered Machines

Häftad Engelska, 2013-10-03
1049
  • Skickas inom 10-15 vardagar.
  • Gratis frakt inom Sverige över 199 kr för privatpersoner.
Finns även som
Visa alla 1 format & utgåvor
Computer Science Workbench is a monograph series which will provide you with an in-depth working knowledge of current developments in computer technology. Every volume in this series will deal with a topic of importance in computer science and elaborate on how you yourself can build systems related to the main theme. You will be able to develop a variety of systems, including computer software tools, computer graphics, computer animation, database management systems, and computer-aided design and manufacturing systems. Computer Science Work bench represents an important new contribution in the field of practical computer technology. Tosiyasu L. Kunii Preface With the advent of digital computers some five decades ago and the wide spread use of computer networks recently, we have gained enormous power in gathering information and manufacturing. Yet, this increase in comput ing power has not given us freedom in a real sense, we are increasingly enslaved by the very machine we built for gaining freedom and efficiency. Making machines to serve mankind is an essential issue we are facing. Building human-centered systems is an imperative task for scientists and engineers in the new millennium. The topic of human-centered servant modules covers a vast area. In our projects we have focused our efforts on developing theories and techn!ques based on fuzzy theories. Chapters 2 to 12 in this book collectively deal with the theoretical, methodological, and applicational aspects of human centered systems. Each chapter presents the most recent research results by the authors on a particular topic.
Visa hela texten

Passar bra ihop

  1. Soft Computing and Human-Centered Machines
  2. +
  3. Designing Data-Intensive Applications

De som köpt den här boken har ofta också köpt Designing Data-Intensive Applications av Martin Kleppmann (häftad).

Köp båda 2 för 1398 kr

Kundrecensioner

Har du läst boken? Sätt ditt betyg »

Fler böcker av författarna

  • The Legend of Zelda: Hyrule Historia

    S Miyamoto, E Aonuma

    Dark Horse Books and Nintendo team up to bring you The Legend of Zelda: Hyrule Historia, containing an unparalleled collection of historical information on The Legend of Zelda franchise. This handsome hardcover contains never-before-seen concept a...

  • Fuzzy Sets in Information Retrieval and Cluster Analysis

    S Miyamoto

    The present monograph intends to establish a solid link among three fields: fuzzy set theory, information retrieval, and cluster analysis. Fuzzy set theory supplies new concepts and methods for the other two fields, and provides a common frame wor...

Innehållsförteckning

1 Introduction.- 1.1 The Third Industrial Revolution: human-centered machines.- 1.2 Soft Computing: a unifying framework for intelligent systems.- 2 Multisets and Fuzzy Multisets.- 2.1 Introduction.- 2.2 Multisets.- 2.3 Fuzzy Multisets.- 2.3.1 Basic Operations of Fuzzy Multisets.- 2.4 Infinite Fuzzy Multisets.- 2.4.1 Infinite Sequence of Memberships and Computability.- 2.4.2 Operations for Infinite Fuzzy Multisets.- 2.5 Another Ftizzification.- 2.6 Application to Query Language for Fuzzy Database.- 2.6.1 Fuzzy Multirelations.- 2.6.2 Functions in Fuzzy SQL.- 2.7 Conclusion.- 2.8 References.- 3 Modal Logic, Rough Sets, and Fuzzy Sets.- 3.1 Introduction.- 3.2 Language for Modal Logic.- 3.3 Kripke Semantics for Modal Logic.- 3.4 Truth Sets and Generalized Lower and Upper Approximations.- 3.5 Validity.- 3.6 What is a System of Modal Logic?.- 3.7 Normal Systems of Modal Logic.- 3.8 Soundness.- 3.9 Completeness.- 3.10 Fuzzy Sets and Rough Sets.- 3.11 Concluding Remarks.- 3.12 References.- 4 Fuzzy Cognitive Maps: Analysis and Extensions.- 4.1 Introduction.- 4.2 Fuzzy Cognitive Maps.- 4.2.1 Causality and Logical Implication.- 4.2.2 Building Fuzzy Cognitive Maps.- 4.2.3 Causal Inference in FCM.- 4.2.4 Combining Fuzzy Cognitive Maps.- 4.3 Extensions to FCM.- 4.3.1 FCM with Non-linear Edge Functions.- 4.3.2 FCM with Constant Time-Delays.- 4.3.3 Weighted Combination of FCMs.- 4.4 Analysis of Fuzzy Cognitive Maps.- 4.4.1 FCM and Its State Space.- 4.4.2 Causal Module of FCM.- 4.4.3 Inference Patterns of Basic FCMs.- 4.4.4 Inference Pattern of General FCMs.- 4.5 Conclusions.- 4.6 References.- 5 Methods in Hard and Fuzzy Clustering.- 5.1 Introduction.- 5.2 Basic Methods in Clustering.- 5.3 Fuzzy c-Means.- 5.4 Other Nonhierarchical Methods.- 5.5 A Numerical Example.- 5.6 Fuzzy Hierarchical Clustering.- 5.7 Conclusions.- 5.8 References.- 6 Soft-Competitive Learning Paradigms.- 6.1 Introduction.- 6.2 Learning by Neural Networks.- 6.2.1 Supervised Learning.- 6.2.2 Unsupervised Learning.- 6.2.3 Reinforcement Learning.- 6.3 Competitive Learning Paradigm.- 6.3.1 Classic Competitive Learning.- 6.4 Overview of Competitive Learning Schemes.- 6.4.1 Winner-Take-Most (WTM) Paradigm.- 6.4.2 Competitive Learning with Conscience.- 6.4.3 Penalizing in Competitive Learning.- 6.4.4 Learning Schemes with Variable Number of Prototypes.- 6.4.5 Fuzzy Clustering Algorithms.- 6.5 Fuzzy Competitive Learning and Soft Competition.- 6.5.1 Conscience and Frequency Sensitive Competitive Learning.- 6.5.2 Rival Penalized Competitive Learning.- 6.6 Compensated Competitive Learning.- 6.6.1 The Concept of Compensated Competitive Learning.- 6.6.2 Varying the Number of Penalized Vectors in CCL.- 6.7 Conclusions.- 6.8 References.- 7 Aggregation Operations for Fusing Fuzzy Information.- 7.1 Introduction.- 7.2 Intersection and Union of Fuzzy Sets.- 7.3 Weighted Unions and Intersections.- 7.4 Uninorms.- 7.5 Mean Aggregation Operators.- 7.6 Ordered Weighted Averaging Operators.- 7.7 Linguistic Quantifiers and OWA Operators.- 7.8 Aggregation Using Fuzzy Measures.- 7.9 Conclusion.- 7.10 References.- 8 Fuzzy Gated Neural Networks in Pattern Recognition.- 8.1 Introduction.- 8.2 Generalized Gated Neuron Model.- 8.3 Fuzzy Gated Neural Networks.- 8.3.1 System Structure.- 8.3.2 Input, Gate, and Output Functions.- 8.3.3 Temporal Aggregation.- 8.4 Comparison between FGNN and STFM.- 8.4.1 FGNN's Operational Characteristics.- 8.5 Experimental Results.- 8.5.1 2D Real World Texture Data.- 8.5.2 3D Synthetic Images.- 8.5.3 Real Range Images.- 8.5.4 Results and Discussions.- 8.6 Improvements to FGNN.- 8.6.1 Performance under Noisy Data.- 8.6.2 Noise Cover in FGNN.- 8.6.3 Knowledge Acquisition and Aggregation.- 8.7 The Improved FGNN.- 8.7.1 Mean and Bayesian Aggregation Methods.- 8.7.2 Alternative Aggregation Methods.- 8.8 Conclusions.- 8.9 References.- 9 Soft Computing Technique in Kansei (Emotional) Information Processing.- 9.1 Introduction.- 9.2 Concept of Kansei Information.- 9.2.1 Difference Betwe