close
1.

電子ブック
ＥＢ
1. Representation and Management of Narrative Information
Gian Piero Zarri
出版情報: Springer eBooks Computer Science , Springer London, 2009
所蔵情報: loading…
目次情報: 続きを見る
Basic Principles / 1：
Narrative Information in an NKRL Context / 1.1：
Narratology and NKRL / 1.1.1：
The Notion of "Event" in an NKRL Context / 1.1.2：
Knowledge Representation and NKRL / 1.2：
"Standard" Ontologies and the "n-ary" Problem / 1.2.1：
A Plain "n-ary" Solution and Some Related Problems / 1.2.2：
In the Guise of Winding Up / 1.3：
The Knowledge Representation Strategy / 2：
Architecture of NKRL: the Four "Components" / 2.1：
The Data Structures of the Four Components / 2.2：
Definitional/Enumerative Data Structures / 2.2.1：
Descriptive/Factual Data Structures / 2.2.2：
Second-order Structures / 2.3：
The Completive Construction / 2.3.1：
Binding Occurrences / 2.3.2：
The Semantic and Ontological Contents / 2.4：
The Organization of the HClass Hierarchy / 3.1：
General Notions about Ontologies / 3.1.1：
HClass Architecture / 3.1.2：
The Organization of the HTemp Hierarchy / 3.2：
Recent Examples of "Structured" Ontological Systems / 3.2.1：
Main Features of Some Specific HTemp Structures / 3.2.2：
The Query and Inference Procedures / 3.3：
"Search Patterns" and Low-level Inferences / 4.1：
The Algorithmic Structure of Fum / 4.1.1：
Temporal Information and Indexing / 4.1.2：
High-level Inference Procedures / 4.2：
General Remarks about Some Reasoning Paradigms / 4.2.1：
Hypothesis Rules / 4.2.2：
Transformation Rules / 4.2.3：
Integrating the Two Main Inferencing Modes of NKRL / 4.2.4：
Inference Rules and Internet Filtering / 4.2.5：
Conclusion / 4.3：
Technological Enhancements / 5.1：
Theoretical Enhancements / 5.2：
Appendix A
Appendix B
References
Index
Basic Principles / 1：
Narrative Information in an NKRL Context / 1.1：
Narratology and NKRL / 1.1.1：
2.

電子ブック
ＥＢ
2. Representation and Management of Narrative Information
Gian Piero Zarri
出版情報: SpringerLink Books - AutoHoldings , Springer London, 2009
所蔵情報: loading…
目次情報: 続きを見る
Basic Principles / 1：
Narrative Information in an NKRL Context / 1.1：
Narratology and NKRL / 1.1.1：
The Notion of "Event" in an NKRL Context / 1.1.2：
Knowledge Representation and NKRL / 1.2：
"Standard" Ontologies and the "n-ary" Problem / 1.2.1：
A Plain "n-ary" Solution and Some Related Problems / 1.2.2：
In the Guise of Winding Up / 1.3：
The Knowledge Representation Strategy / 2：
Architecture of NKRL: the Four "Components" / 2.1：
The Data Structures of the Four Components / 2.2：
Definitional/Enumerative Data Structures / 2.2.1：
Descriptive/Factual Data Structures / 2.2.2：
Second-order Structures / 2.3：
The Completive Construction / 2.3.1：
Binding Occurrences / 2.3.2：
The Semantic and Ontological Contents / 2.4：
The Organization of the HClass Hierarchy / 3.1：
General Notions about Ontologies / 3.1.1：
HClass Architecture / 3.1.2：
The Organization of the HTemp Hierarchy / 3.2：
Recent Examples of "Structured" Ontological Systems / 3.2.1：
Main Features of Some Specific HTemp Structures / 3.2.2：
The Query and Inference Procedures / 3.3：
"Search Patterns" and Low-level Inferences / 4.1：
The Algorithmic Structure of Fum / 4.1.1：
Temporal Information and Indexing / 4.1.2：
High-level Inference Procedures / 4.2：
General Remarks about Some Reasoning Paradigms / 4.2.1：
Hypothesis Rules / 4.2.2：
Transformation Rules / 4.2.3：
Integrating the Two Main Inferencing Modes of NKRL / 4.2.4：
Inference Rules and Internet Filtering / 4.2.5：
Conclusion / 4.3：
Technological Enhancements / 5.1：
Theoretical Enhancements / 5.2：
Appendix A
Appendix B
References
Index
Basic Principles / 1：
Narrative Information in an NKRL Context / 1.1：
Narratology and NKRL / 1.1.1：
3.

電子ブック
ＥＢ
3. Motivated Reinforcement Learning
Kathryn E. Merrick, Mary Lou Maher
出版情報: Springer eBooks Computer Science , Springer Berlin Heidelberg, 2009
所蔵情報: loading…
目次情報: 続きを見る
Non-Player Characters and Reinforcement Learning / Part I：
Non-Player Characters in Multiuser Games / 1：
Types of Multiuser Games / 1.1：
Massively Multiplayer Online Role-Playing Games / 1.1.1：
Multiuser Simulation Games / 1.1.2：
Open-Ended Virtual Worlds / 1.1.3：
Character Roles in Multiuser Games / 1.2：
Existing Artificial Intelligence Techniques for Non-Player Characters in Multiuser Games / 1.3：
Reflexive Agents / 1.3.1：
Learning Agents / 1.3.2：
Evolutionary Agents / 1.3.3：
Smart Terrain / 1.3.4：
Summary / 1.4：
References / 1.5：
Motivation in Natural and Artificial Agents / 2：
Defining Motivation / 2.1：
Biological Theories of Motivation / 2.2：
Drive Theory / 2.2.1：
Motivational State Theory / 2.2.2：
Arousal / 2.2.3：
Cognitive Theories of Motivation / 2.3：
Curiosity / 2.3.1：
Operant Theory / 2.3.2：
Incentive / 2.3.3：
Achievement Motivation / 2.3.4：
Attribution Theory / 2.3.5：
Intrinsic Motivation / 2.3.6：
Social Theories of Motivation / 2.4：
Conformity / 2.4.1：
Cultural Effect / 2.4.2：
Evolution / 2.4.3：
Combined Motivation Theories / 2.5：
Maslow's Hierarchy of Needs / 2.5.1：
Existence Relatedness Growth Theory / 2.5.2：
Towards Motivated Reinforcement Learning / 2.6：
Defining Reinforcement Learning / 3.1：
Dynamic Programming / 3.1.1：
Monte Carlo Methods / 3.1.2：
Temporal Difference Learning / 3.1.3：
Reinforcement Learning in Complex Environments / 3.2：
Partially Observable Environments / 3.2.1：
Function Approximation / 3.2.2：
Hierarchical Reinforcement Learning / 3.2.3：
Motivated Reinforcement Learning / 3.3：
Using a Motivation Signal in Addition to a Reward Signal / 3.3.1：
Using a Motivation Signal Instead of a Reward Signal / 3.3.2：
Comparing the Behaviour of Learning Agents / 3.4：
Player Satisfaction / 4.1：
Psychological Flow / 4.1.1：
Structural Flow / 4.1.2：
Formalising Non-Player Character Behaviour / 4.2：
Models of Optimality for Reinforcement Learning / 4.2.1：
Characteristics of Motivated Reinforcement Learning / 4.2.2：
Comparing Motivated Reinforcement Learning Agents / 4.3：
Statistical Model for Identifying Learned Tasks / 4.3.1：
Behavioural Variety / 4.3.2：
Behavioural Complexity / 4.3.3：
Developing Curious Characters Using Motivated Reinforcement Learning / 4.4：
Curiosity, Motivation and Attention Focus / 5：
Agents in Complex, Dynamic Environments / 5.1：
States / 5.1.1：
Actions / 5.1.2：
Reward and Motivation / 5.1.3：
Motivation and Attention Focus / 5.2：
Observations / 5.2.1：
Events / 5.2.2：
Tasks and Task Selection / 5.2.3：
Experience-Based Reward as Cognitive Motivation / 5.2.4：
Arbitration Functions / 5.2.5：
A General Experience-Based Motivation Function / 5.2.6：
Curiosity as Motivation for Support Characters / 5.3：
Curiosity as Interesting Events / 5.3.1：
Curiosity as Interesting and Competence / 5.3.2：
Motivated Reinforcement Learning Agents / 5.4：
A General Motivated Reinforcement Learning Model / 6.1：
Algorithms for Motivated Reinforcement Learning / 6.2：
Motivated Flat Reinforcement Learning / 6.2.1：
Motivated Multioption Reinforcement Learning / 6.2.2：
Motivated Hierarchical Reinforcement Learning / 6.2.3：
Curious Characters in Games / 6.3：
Curious Characters for Multiuser Games / 7：
Motivated Reinforcement Learning for Support Characters in Massively Multiplayer Online Role-Playing Games / 7.1：
Character Behaviour in Small-Scale, Isolated Games Locations / 7.2：
Case Studies of Individual Characters / 7.2.1：
General Trends in Character Behaviour / 7.2.2：
Curious Characters for Games in Complex, Dynamic Environments / 7.3：
Designing Characters That Can Multitask / 8.1：
Designing Characters for Complex Tasks / 8.1.1：
Games That Change While Characters Are Learning / 8.2.1：
Curious Characters for Games in Second Life / 8.3.1：
Motivated Reinforcement Learning in Open-Ended Simulation Games / 9.1：
Game Design / 9.1.1：
Character Design / 9.1.2：
Evaluating Character Behaviour in Response to Game Play Sequences / 9.2：
Discussion / 9.2.1：
Future / 9.3：
Towards the Future / 10：
Using Motivated Reinforcement Learning in Non-Player Characters / 10.1：
Other Gaming Applications for Motivated Reinforcement Learning / 10.2：
Dynamic Difficulty Adjustment / 10.2.1：
Procedural Content Generation / 10.2.2：
Beyond Curiosity / 10.3：
Biological Models of Motivation / 10.3.1：
Cognitive Models of Motivation / 10.3.2：
Social Models of Motivation / 10.3.3：
Combined Models of Motivation / 10.3.4：
New Models of Motivated Learning / 10.4：
Motivated Supervised Learning / 10.4.1：
Motivated Unsupervised Learning / 10.4.2：
Evaluating the Behaviour of Motivated Learning Agents / 10.5：
Concluding Remarks / 10.6：
Index / 10.7：
Non-Player Characters and Reinforcement Learning / Part I：
Non-Player Characters in Multiuser Games / 1：
Types of Multiuser Games / 1.1：
4.

電子ブック
ＥＢ
4. Motivated Reinforcement Learning
Kathryn E. Merrick, Mary Lou Maher
出版情報: SpringerLink Books - AutoHoldings , Springer Berlin Heidelberg, 2009
所蔵情報: loading…
目次情報: 続きを見る
Non-Player Characters and Reinforcement Learning / Part I：
Non-Player Characters in Multiuser Games / 1：
Types of Multiuser Games / 1.1：
Massively Multiplayer Online Role-Playing Games / 1.1.1：
Multiuser Simulation Games / 1.1.2：
Open-Ended Virtual Worlds / 1.1.3：
Character Roles in Multiuser Games / 1.2：
Existing Artificial Intelligence Techniques for Non-Player Characters in Multiuser Games / 1.3：
Reflexive Agents / 1.3.1：
Learning Agents / 1.3.2：
Evolutionary Agents / 1.3.3：
Smart Terrain / 1.3.4：
Summary / 1.4：
References / 1.5：
Motivation in Natural and Artificial Agents / 2：
Defining Motivation / 2.1：
Biological Theories of Motivation / 2.2：
Drive Theory / 2.2.1：
Motivational State Theory / 2.2.2：
Arousal / 2.2.3：
Cognitive Theories of Motivation / 2.3：
Curiosity / 2.3.1：
Operant Theory / 2.3.2：
Incentive / 2.3.3：
Achievement Motivation / 2.3.4：
Attribution Theory / 2.3.5：
Intrinsic Motivation / 2.3.6：
Social Theories of Motivation / 2.4：
Conformity / 2.4.1：
Cultural Effect / 2.4.2：
Evolution / 2.4.3：
Combined Motivation Theories / 2.5：
Maslow's Hierarchy of Needs / 2.5.1：
Existence Relatedness Growth Theory / 2.5.2：
Towards Motivated Reinforcement Learning / 2.6：
Defining Reinforcement Learning / 3.1：
Dynamic Programming / 3.1.1：
Monte Carlo Methods / 3.1.2：
Temporal Difference Learning / 3.1.3：
Reinforcement Learning in Complex Environments / 3.2：
Partially Observable Environments / 3.2.1：
Function Approximation / 3.2.2：
Hierarchical Reinforcement Learning / 3.2.3：
Motivated Reinforcement Learning / 3.3：
Using a Motivation Signal in Addition to a Reward Signal / 3.3.1：
Using a Motivation Signal Instead of a Reward Signal / 3.3.2：
Comparing the Behaviour of Learning Agents / 3.4：
Player Satisfaction / 4.1：
Psychological Flow / 4.1.1：
Structural Flow / 4.1.2：
Formalising Non-Player Character Behaviour / 4.2：
Models of Optimality for Reinforcement Learning / 4.2.1：
Characteristics of Motivated Reinforcement Learning / 4.2.2：
Comparing Motivated Reinforcement Learning Agents / 4.3：
Statistical Model for Identifying Learned Tasks / 4.3.1：
Behavioural Variety / 4.3.2：
Behavioural Complexity / 4.3.3：
Developing Curious Characters Using Motivated Reinforcement Learning / 4.4：
Curiosity, Motivation and Attention Focus / 5：
Agents in Complex, Dynamic Environments / 5.1：
States / 5.1.1：
Actions / 5.1.2：
Reward and Motivation / 5.1.3：
Motivation and Attention Focus / 5.2：
Observations / 5.2.1：
Events / 5.2.2：
Tasks and Task Selection / 5.2.3：
Experience-Based Reward as Cognitive Motivation / 5.2.4：
Arbitration Functions / 5.2.5：
A General Experience-Based Motivation Function / 5.2.6：
Curiosity as Motivation for Support Characters / 5.3：
Curiosity as Interesting Events / 5.3.1：
Curiosity as Interesting and Competence / 5.3.2：
Motivated Reinforcement Learning Agents / 5.4：
A General Motivated Reinforcement Learning Model / 6.1：
Algorithms for Motivated Reinforcement Learning / 6.2：
Motivated Flat Reinforcement Learning / 6.2.1：
Motivated Multioption Reinforcement Learning / 6.2.2：
Motivated Hierarchical Reinforcement Learning / 6.2.3：
Curious Characters in Games / 6.3：
Curious Characters for Multiuser Games / 7：
Motivated Reinforcement Learning for Support Characters in Massively Multiplayer Online Role-Playing Games / 7.1：
Character Behaviour in Small-Scale, Isolated Games Locations / 7.2：
Case Studies of Individual Characters / 7.2.1：
General Trends in Character Behaviour / 7.2.2：
Curious Characters for Games in Complex, Dynamic Environments / 7.3：
Designing Characters That Can Multitask / 8.1：
Designing Characters for Complex Tasks / 8.1.1：
Games That Change While Characters Are Learning / 8.2.1：
Curious Characters for Games in Second Life / 8.3.1：
Motivated Reinforcement Learning in Open-Ended Simulation Games / 9.1：
Game Design / 9.1.1：
Character Design / 9.1.2：
Evaluating Character Behaviour in Response to Game Play Sequences / 9.2：
Discussion / 9.2.1：
Future / 9.3：
Towards the Future / 10：
Using Motivated Reinforcement Learning in Non-Player Characters / 10.1：
Other Gaming Applications for Motivated Reinforcement Learning / 10.2：
Dynamic Difficulty Adjustment / 10.2.1：
Procedural Content Generation / 10.2.2：
Beyond Curiosity / 10.3：
Biological Models of Motivation / 10.3.1：
Cognitive Models of Motivation / 10.3.2：
Social Models of Motivation / 10.3.3：
Combined Models of Motivation / 10.3.4：
New Models of Motivated Learning / 10.4：
Motivated Supervised Learning / 10.4.1：
Motivated Unsupervised Learning / 10.4.2：
Evaluating the Behaviour of Motivated Learning Agents / 10.5：
Concluding Remarks / 10.6：
Index / 10.7：
Non-Player Characters and Reinforcement Learning / Part I：
Non-Player Characters in Multiuser Games / 1：
Types of Multiuser Games / 1.1：
5.

電子ブック
ＥＢ
5. Automata for Branching and Layered Temporal Structures
Gabriele Puppis, Takeo Kanade
出版情報: Springer eBooks Computer Science , Springer Berlin Heidelberg, 2010
所蔵情報: loading…
目次情報: 続きを見る
Introduction / 1：
Word Automata and Time Granularities / 2：
Background Knowledge / 2.1：
Words and Languages / 2.1.1：
Periodicity of Words / 2.1.2：
Word Automata / 2.1.3：
Time Granularities / 2.1.4：
The String-Based and Automaton-Based Approaches / 2.2：
The Granspec Formalism / 2.2.1：
From Granspecs to Single-String Automata / 2.2.2：
Counters and Multiple Transitions / 2.2.3：
The Logical Counterpart of RCSSA / 2.2.4：
Compact and Tractable Representations / 2.3：
Nested Repetitions of Words / 2.3.1：
Algorithms on NCSSA / 2.3.2：
Optimizing Representations / 2.3.3：
Reasoning on Sets of Granularities / 2.4：
Languages of Ultimately Periodic Words / 2.4.1：
Ultimately Periodic Automata / 2.4.2：
Algorithms on UPA / 2.4.3：
Applications to Time Granularity / 2.4.4：
Discussion / 2.5：
Tree Automata and Logics / 3：
Graphs and Trees / 3.1：
Tree Automata / 3.1.2：
Monadic Second-Order Logic / 3.1.3：
The Model Checking Problem / 3.1.4：
The Contraction Method for Tree Automata / 3.2：
Features and Types / 3.2.1：
Types and the Acceptance Problem / 3.2.2：
From Trees to Their Retractions / 3.2.3：
An Example / 3.2.4：
Tree Transformations / 3.3：
Tree Recolorings / 3.3.1：
Tree Substitutions / 3.3.2：
Tree Transducers / 3.3.3：
Inverse Substitutions / 3.3.4：
A Summary / 3.3.5：
The Class of Reducible Trees / 3.4：
Compositional Properties of Types / 3.4.1：
Closure Properties / 3.4.2：
Effectiveness of the Contraction Method / 3.5：
Reducible Trees and the Caucal Hierarchy / 3.5.1：
Two-Way Alternating Tree Automata / 3.5.2：
Morphic Trees / 3.5.3：
Layered Temporal Structures / 3.5.4：
Summary / 3.6：
Technical Proofs / A：
Proofs of Theorem 5 and Theorem 6 / A.l：
Proof of Theorem 8 / A.2：
Proof of Proposition 34 / A.3：
References
Notation
Index
Introduction / 1：
Word Automata and Time Granularities / 2：
Background Knowledge / 2.1：
6.

電子ブック
ＥＢ
6. Automata for Branching and Layered Temporal Structures
Gabriele Puppis, Takeo Kanade
出版情報: SpringerLink Books - AutoHoldings , Springer Berlin Heidelberg, 2010
所蔵情報: loading…
目次情報: 続きを見る
Introduction / 1：
Word Automata and Time Granularities / 2：
Background Knowledge / 2.1：
Words and Languages / 2.1.1：
Periodicity of Words / 2.1.2：
Word Automata / 2.1.3：
Time Granularities / 2.1.4：
The String-Based and Automaton-Based Approaches / 2.2：
The Granspec Formalism / 2.2.1：
From Granspecs to Single-String Automata / 2.2.2：
Counters and Multiple Transitions / 2.2.3：
The Logical Counterpart of RCSSA / 2.2.4：
Compact and Tractable Representations / 2.3：
Nested Repetitions of Words / 2.3.1：
Algorithms on NCSSA / 2.3.2：
Optimizing Representations / 2.3.3：
Reasoning on Sets of Granularities / 2.4：
Languages of Ultimately Periodic Words / 2.4.1：
Ultimately Periodic Automata / 2.4.2：
Algorithms on UPA / 2.4.3：
Applications to Time Granularity / 2.4.4：
Discussion / 2.5：
Tree Automata and Logics / 3：
Graphs and Trees / 3.1：
Tree Automata / 3.1.2：
Monadic Second-Order Logic / 3.1.3：
The Model Checking Problem / 3.1.4：
The Contraction Method for Tree Automata / 3.2：
Features and Types / 3.2.1：
Types and the Acceptance Problem / 3.2.2：
From Trees to Their Retractions / 3.2.3：
An Example / 3.2.4：
Tree Transformations / 3.3：
Tree Recolorings / 3.3.1：
Tree Substitutions / 3.3.2：
Tree Transducers / 3.3.3：
Inverse Substitutions / 3.3.4：
A Summary / 3.3.5：
The Class of Reducible Trees / 3.4：
Compositional Properties of Types / 3.4.1：
Closure Properties / 3.4.2：
Effectiveness of the Contraction Method / 3.5：
Reducible Trees and the Caucal Hierarchy / 3.5.1：
Two-Way Alternating Tree Automata / 3.5.2：
Morphic Trees / 3.5.3：
Layered Temporal Structures / 3.5.4：
Summary / 3.6：
Technical Proofs / A：
Proofs of Theorem 5 and Theorem 6 / A.l：
Proof of Theorem 8 / A.2：
Proof of Proposition 34 / A.3：
References
Notation
Index
Introduction / 1：
Word Automata and Time Granularities / 2：
Background Knowledge / 2.1：
7.

電子ブック
ＥＢ
7. On Probabilistic Conditional Independence Structures
Milan Studen?, Michael Jordan, Frank P. Kelly, Jon Kleinberg, Bernhard Sch?lkopf, Ian Witten
出版情報: Springer eBooks Computer Science , Springer London, 2005
所蔵情報: loading…
目次情報: 続きを見る
Introduction / 1：
Motivational thoughts / 1.1：
Goals of the monograph / 1.2：
Structure of the book / 1.3：
Basic Concepts / 2：
Conditional independence / 2.1：
Semi-graphoid properties / 2.2：
Formal independence models / 2.2.1：
Semi-graphoids / 2.2.2：
Elementary independence statements / 2.2.3：
Problem of axiomatic characterization / 2.2.4：
Classes of probability measures / 2.3：
Marginally continuous measures / 2.3.1：
Factorizable measures / 2.3.2：
Multiinformation and conditional product / 2.3.3：
Properties of multiinformation function / 2.3.4：
Positive measures / 2.3.5：
Gaussian measures / 2.3.6：
Basic construction / 2.3.7：
Imsets / 2.4：
Graphical Methods / 3：
Undirected graphs / 3.1：
Acyclic directed graphs / 3.2：
Classic chain graphs / 3.3：
Within classic graphical models / 3.4：
Decomposable models / 3.4.1：
Recursive causal graphs / 3.4.2：
Lattice conditional independence models / 3.4.3：
Bubble graphs / 3.4.4：
Advanced graphical models / 3.5：
General directed graphs / 3.5.1：
Reciprocal graphs / 3.5.2：
Joint-response chain graphs / 3.5.3：
Covariance graphs / 3.5.4：
Alternative chain graphs / 3.5.5：
Annotated graphs / 3.5.6：
Hidden variables / 3.5.7：
Ancestral graphs / 3.5.8：
MC graphs / 3.5.9：
Incompleteness of graphical approaches / 3.6：
Structural Imsets: Fundamentals / 4：
Basic class of distributions / 4.1：
Discrete measures / 4.1.1：
Regular Gaussian measures / 4.1.2：
Conditional Gaussian measures / 4.1.3：
Classes of structural imsets / 4.2：
Elementary imsets / 4.2.1：
Semi-elementary and combinatorial imsets / 4.2.2：
Structural imsets / 4.2.3：
Product formula induced by a structural imset / 4.3：
Examples of reference systems of measures / 4.3.1：
Topological assumptions / 4.3.2：
Markov condition / 4.4：
Semi-graphoid induced by a structural imset / 4.4.1：
Markovian measures / 4.4.2：
Equivalence result / 4.5：
Description of Probabilistic Models / 5：
Supermodular set functions / 5.1：
Semi-graphoid produced by a supermodular function / 5.1.1：
Quantitative equivalence of supermodular functions / 5.1.2：
Skeletal supermodular functions / 5.2：
Skeleton / 5.2.1：
Significance of skeletal imsets / 5.2.2：
Description of models by structural imsets / 5.3：
Galois connection / 5.4：
Formal concept analysis / 5.4.1：
Lattice of structural models / 5.4.2：
Equivalence and Implication / 6：
Two concepts of equivalence / 6.1：
Independence and Markov equivalence / 6.1.1：
Independence implication / 6.2：
Direct characterization of independence implication / 6.2.1：
Skeletal characterization of independence implication / 6.2.2：
Testing independence implication / 6.3：
Testing structural imsets / 6.3.1：
Grade / 6.3.2：
Invariants of independence equivalence / 6.4：
Adaptation to a distribution framework / 6.5：
The Problem of Representative Choice / 7：
Baricentral imsets / 7.1：
Standard imsets / 7.2：
Translation of DAG models / 7.2.1：
Translation of decomposable models / 7.2.2：
Imsets of the smallest degree / 7.3：
Decomposition implication / 7.3.1：
Minimal generators / 7.3.2：
Span / 7.4：
Determining and unimarginal classes / 7.4.1：
Imsets with the least lower class / 7.4.2：
Exclusivity of standard imsets / 7.4.3：
Dual description / 7.5：
Coportraits / 7.5.1：
Dual baricentral imsets and global view / 7.5.2：
Learning / 8：
Two approaches to learning / 8.1：
Quality criteria / 8.2：
Criteria for learning DAG models / 8.2.1：
Score equivalent criteria / 8.2.2：
Decomposable criteria / 8.2.3：
Regular criteria / 8.2.4：
Inclusion neighborhood / 8.3：
Standard imsets and learning / 8.4：
Inclusion neighborhood characterization / 8.4.1：
Regular criteria and standard imsets / 8.4.2：
Open Problems / 9：
Theoretical problems / 9.1：
Miscellaneous topics / 9.1.1：
Classification of skeletal imsets / 9.1.2：
Operations with structural models / 9.2：
Reductive operations / 9.2.1：
Expansive operations / 9.2.2：
Cumulative operations / 9.2.3：
Decomposition of structural models / 9.2.4：
Implementation tasks / 9.3：
Interpretation and learning tasks / 9.4：
Meaningful description of structural models / 9.4.1：
Tasks concerning distribution frameworks / 9.4.2：
Learning tasks / 9.4.3：
Appendix / A：
Classes of sets / A.1：
Posets and lattices / A.2：
Graphs / A.3：
Topological concepts / A.4：
Finite-dimensional subspaces and convex cones / A.5：
Linear subspaces / A.5.1：
Convex sets and cones / A.5.2：
Measure-theoretical concepts / A.6：
Measure and integral / A.6.1：
Basic measure-theoretical results / A.6.2：
Information-theoretical concepts / A.6.3：
Conditional probability / A.6.4：
Conditional independence in terms of ?-algebras / A.7：
Concepts from multivariate analysis / A.8：
Matrices / A.8.1：
Statistical characteristics of probability measures / A.8.2：
Multivariate Gaussian distributions / A.8.3：
Elementary statistical concepts / A.9：
Empirical concepts / A.9.1：
Statistical conception / A.9.2：
Likelihood function / A.9.3：
Testing statistical hypotheses / A.9.4：
Distribution framework / A.9.5：
List of Notation
List of Lemmas, Propositions etc
References
Index
Introduction / 1：
Motivational thoughts / 1.1：
Goals of the monograph / 1.2：
8.

電子ブック
ＥＢ
8. On Probabilistic Conditional Independence Structures
Milan Studený, Michael Jordan, Frank P. Kelly, Jon Kleinberg, Bernhard Schölkopf, Ian Witten
出版情報: SpringerLink Books - AutoHoldings , Springer London, 2005
所蔵情報: loading…
目次情報: 続きを見る
Introduction / 1：
Motivational thoughts / 1.1：
Goals of the monograph / 1.2：
Structure of the book / 1.3：
Basic Concepts / 2：
Conditional independence / 2.1：
Semi-graphoid properties / 2.2：
Formal independence models / 2.2.1：
Semi-graphoids / 2.2.2：
Elementary independence statements / 2.2.3：
Problem of axiomatic characterization / 2.2.4：
Classes of probability measures / 2.3：
Marginally continuous measures / 2.3.1：
Factorizable measures / 2.3.2：
Multiinformation and conditional product / 2.3.3：
Properties of multiinformation function / 2.3.4：
Positive measures / 2.3.5：
Gaussian measures / 2.3.6：
Basic construction / 2.3.7：
Imsets / 2.4：
Graphical Methods / 3：
Undirected graphs / 3.1：
Acyclic directed graphs / 3.2：
Classic chain graphs / 3.3：
Within classic graphical models / 3.4：
Decomposable models / 3.4.1：
Recursive causal graphs / 3.4.2：
Lattice conditional independence models / 3.4.3：
Bubble graphs / 3.4.4：
Advanced graphical models / 3.5：
General directed graphs / 3.5.1：
Reciprocal graphs / 3.5.2：
Joint-response chain graphs / 3.5.3：
Covariance graphs / 3.5.4：
Alternative chain graphs / 3.5.5：
Annotated graphs / 3.5.6：
Hidden variables / 3.5.7：
Ancestral graphs / 3.5.8：
MC graphs / 3.5.9：
Incompleteness of graphical approaches / 3.6：
Structural Imsets: Fundamentals / 4：
Basic class of distributions / 4.1：
Discrete measures / 4.1.1：
Regular Gaussian measures / 4.1.2：
Conditional Gaussian measures / 4.1.3：
Classes of structural imsets / 4.2：
Elementary imsets / 4.2.1：
Semi-elementary and combinatorial imsets / 4.2.2：
Structural imsets / 4.2.3：
Product formula induced by a structural imset / 4.3：
Examples of reference systems of measures / 4.3.1：
Topological assumptions / 4.3.2：
Markov condition / 4.4：
Semi-graphoid induced by a structural imset / 4.4.1：
Markovian measures / 4.4.2：
Equivalence result / 4.5：
Description of Probabilistic Models / 5：
Supermodular set functions / 5.1：
Semi-graphoid produced by a supermodular function / 5.1.1：
Quantitative equivalence of supermodular functions / 5.1.2：
Skeletal supermodular functions / 5.2：
Skeleton / 5.2.1：
Significance of skeletal imsets / 5.2.2：
Description of models by structural imsets / 5.3：
Galois connection / 5.4：
Formal concept analysis / 5.4.1：
Lattice of structural models / 5.4.2：
Equivalence and Implication / 6：
Two concepts of equivalence / 6.1：
Independence and Markov equivalence / 6.1.1：
Independence implication / 6.2：
Direct characterization of independence implication / 6.2.1：
Skeletal characterization of independence implication / 6.2.2：
Testing independence implication / 6.3：
Testing structural imsets / 6.3.1：
Grade / 6.3.2：
Invariants of independence equivalence / 6.4：
Adaptation to a distribution framework / 6.5：
The Problem of Representative Choice / 7：
Baricentral imsets / 7.1：
Standard imsets / 7.2：
Translation of DAG models / 7.2.1：
Translation of decomposable models / 7.2.2：
Imsets of the smallest degree / 7.3：
Decomposition implication / 7.3.1：
Minimal generators / 7.3.2：
Span / 7.4：
Determining and unimarginal classes / 7.4.1：
Imsets with the least lower class / 7.4.2：
Exclusivity of standard imsets / 7.4.3：
Dual description / 7.5：
Coportraits / 7.5.1：
Dual baricentral imsets and global view / 7.5.2：
Learning / 8：
Two approaches to learning / 8.1：
Quality criteria / 8.2：
Criteria for learning DAG models / 8.2.1：
Score equivalent criteria / 8.2.2：
Decomposable criteria / 8.2.3：
Regular criteria / 8.2.4：
Inclusion neighborhood / 8.3：
Standard imsets and learning / 8.4：
Inclusion neighborhood characterization / 8.4.1：
Regular criteria and standard imsets / 8.4.2：
Open Problems / 9：
Theoretical problems / 9.1：
Miscellaneous topics / 9.1.1：
Classification of skeletal imsets / 9.1.2：
Operations with structural models / 9.2：
Reductive operations / 9.2.1：
Expansive operations / 9.2.2：
Cumulative operations / 9.2.3：
Decomposition of structural models / 9.2.4：
Implementation tasks / 9.3：
Interpretation and learning tasks / 9.4：
Meaningful description of structural models / 9.4.1：
Tasks concerning distribution frameworks / 9.4.2：
Learning tasks / 9.4.3：
Appendix / A：
Classes of sets / A.1：
Posets and lattices / A.2：
Graphs / A.3：
Topological concepts / A.4：
Finite-dimensional subspaces and convex cones / A.5：
Linear subspaces / A.5.1：
Convex sets and cones / A.5.2：
Measure-theoretical concepts / A.6：
Measure and integral / A.6.1：
Basic measure-theoretical results / A.6.2：
Information-theoretical concepts / A.6.3：
Conditional probability / A.6.4：
Conditional independence in terms of ?-algebras / A.7：
Concepts from multivariate analysis / A.8：
Matrices / A.8.1：
Statistical characteristics of probability measures / A.8.2：
Multivariate Gaussian distributions / A.8.3：
Elementary statistical concepts / A.9：
Empirical concepts / A.9.1：
Statistical conception / A.9.2：
Likelihood function / A.9.3：
Testing statistical hypotheses / A.9.4：
Distribution framework / A.9.5：
List of Notation
List of Lemmas, Propositions etc
References
Index
Introduction / 1：
Motivational thoughts / 1.1：
Goals of the monograph / 1.2：
9.

電子ブック
ＥＢ
9. Sensitivity Analysis for Neural Networks
Daniel S. Yeung, Ian Cloete, Wing W. Y. Ng, Daming Shi
出版情報: Springer eBooks Computer Science , Springer Berlin Heidelberg, 2010
所蔵情報: loading…
目次情報: 続きを見る
Introduction to Neural Networks / 1：
Properties of Neural Networks / 1.1：
Neural Network Learning / 1.2：
Supervised Learning / 1.2.1：
Unsupervised Learning / 1.2.2：
Perceptron / 1.3：
Adaline and Least Mean Square Algorithm / 1.4：
Multilayer Perceptron and Backpropagation Algorithm / 1.5：
Output Layer Learning / 1.5.1：
Hidden Layer Learning / 1.5.2：
Radial Basis Function Networks / 1.6：
Support Vector Machines / 1.7：
Principles of Sensitivity Analysis / 2：
Perturbations in Neural Networks / 2.1：
Neural Network Sensitivity Analysis / 2.2：
Fundamental Methods of Sensitivity Analysis / 2.3：
Geometrical Approach / 2.3.1：
Statistical Approach / 2.3.2：
Summary / 2.4：
Hyper-Rectangle Model / 3：
Hyper-Rectangle Model for Input Space of MLP / 3.1：
Sensitivity Measure of MLP / 3.2：
Discussion / 3.3：
Sensitivity Analysis with Parameterized Activation Function / 4：
Parameterized Antisymmetric Squashing Function / 4.1：
Sensitivity Measure / 4.2：
Localized Generalization Error Model / 4.3：
Introduction / 5.1：
The Localized Generalization Error Model / 5.2：
The Q-Neighborhood and Q-Union / 5.2.1：
The Localized Generalization Error Bound / 5.2.2：
Stochastic Sensitivity Measure for RBFNN / 5.2.3：
Characteristics of the Error Bound / 5.2.4：
Comparing Two Classifiers Using the Error Bound / 5.2.5：
Architecture Selection Using the Error Bound / 5.3：
Critical Vector Learning for RBF Networks / 5.3.1：
Related Work / 6.1：
Construction of RBF Networks with Sensitivity Analysis / 6.2：
RBF Classifiers' Sensitivity to the Kernel Function Centers / 6.2.1：
Orthogonal Least Square Transform / 6.2.2：
Critical Vector Selection / 6.2.3：
Sensitivity Analysis of Prior Knowledge / 6.3：
KBANNs / 7.1：
Inductive Bias / 7.2：
Sensitivity Analysis and Measures / 7.3：
Output-Pattern Sensitivity / 7.3.1：
Output-Weight Sensitivity / 7.3.2：
Output-H Sensitivity / 7.3.3：
Euclidean Distance / 7.3.4：
Promoter Recognition / 7.4：
Data and Initial Domain Theory / 7.4.1：
Experimental Methodology / 7.4.2：
Discussion and Conclusion / 7.5：
Applications / 8：
Input Dimension Reduction / 8.1：
Sensitivity Matrix / 8.1.1：
Criteria for Pruning Inputs / 8.1.2：
Network Optimization / 8.2：
Selective Learning / 8.3：
Hardware Robustness / 8.4：
Measure of Nonlinearity / 8.5：
Parameter Tuning for Neocognitron / 8.6：
Receptive Field / 8.6.1：
Selectivity / 8.6.2：
Sensitivity Analysis of the Neocognitron / 8.6.3：
Bibliography
Introduction to Neural Networks / 1：
Properties of Neural Networks / 1.1：
Neural Network Learning / 1.2：
10.

電子ブック
ＥＢ
10. Sensitivity Analysis for Neural Networks
Daniel S. Yeung, Ian Cloete, Wing W. Y. Ng, Daming Shi
出版情報: SpringerLink Books - AutoHoldings , Springer Berlin Heidelberg, 2010
所蔵情報: loading…
目次情報: 続きを見る
Introduction to Neural Networks / 1：
Properties of Neural Networks / 1.1：
Neural Network Learning / 1.2：
Supervised Learning / 1.2.1：
Unsupervised Learning / 1.2.2：
Perceptron / 1.3：
Adaline and Least Mean Square Algorithm / 1.4：
Multilayer Perceptron and Backpropagation Algorithm / 1.5：
Output Layer Learning / 1.5.1：
Hidden Layer Learning / 1.5.2：
Radial Basis Function Networks / 1.6：
Support Vector Machines / 1.7：
Principles of Sensitivity Analysis / 2：
Perturbations in Neural Networks / 2.1：
Neural Network Sensitivity Analysis / 2.2：
Fundamental Methods of Sensitivity Analysis / 2.3：
Geometrical Approach / 2.3.1：
Statistical Approach / 2.3.2：
Summary / 2.4：
Hyper-Rectangle Model / 3：
Hyper-Rectangle Model for Input Space of MLP / 3.1：
Sensitivity Measure of MLP / 3.2：
Discussion / 3.3：
Sensitivity Analysis with Parameterized Activation Function / 4：
Parameterized Antisymmetric Squashing Function / 4.1：
Sensitivity Measure / 4.2：
Localized Generalization Error Model / 4.3：
Introduction / 5.1：
The Localized Generalization Error Model / 5.2：
The Q-Neighborhood and Q-Union / 5.2.1：
The Localized Generalization Error Bound / 5.2.2：
Stochastic Sensitivity Measure for RBFNN / 5.2.3：
Characteristics of the Error Bound / 5.2.4：
Comparing Two Classifiers Using the Error Bound / 5.2.5：
Architecture Selection Using the Error Bound / 5.3：
Critical Vector Learning for RBF Networks / 5.3.1：
Related Work / 6.1：
Construction of RBF Networks with Sensitivity Analysis / 6.2：
RBF Classifiers' Sensitivity to the Kernel Function Centers / 6.2.1：
Orthogonal Least Square Transform / 6.2.2：
Critical Vector Selection / 6.2.3：
Sensitivity Analysis of Prior Knowledge / 6.3：
KBANNs / 7.1：
Inductive Bias / 7.2：
Sensitivity Analysis and Measures / 7.3：
Output-Pattern Sensitivity / 7.3.1：
Output-Weight Sensitivity / 7.3.2：
Output-H Sensitivity / 7.3.3：
Euclidean Distance / 7.3.4：
Promoter Recognition / 7.4：
Data and Initial Domain Theory / 7.4.1：
Experimental Methodology / 7.4.2：
Discussion and Conclusion / 7.5：
Applications / 8：
Input Dimension Reduction / 8.1：
Sensitivity Matrix / 8.1.1：
Criteria for Pruning Inputs / 8.1.2：
Network Optimization / 8.2：
Selective Learning / 8.3：
Hardware Robustness / 8.4：
Measure of Nonlinearity / 8.5：
Parameter Tuning for Neocognitron / 8.6：
Receptive Field / 8.6.1：
Selectivity / 8.6.2：
Sensitivity Analysis of the Neocognitron / 8.6.3：
Bibliography
Introduction to Neural Networks / 1：
Properties of Neural Networks / 1.1：
Neural Network Learning / 1.2：
文献の複写および貸借の依頼を行う
 文献複写・貸借依頼