Ebook: Adaptivity and Learning: An Interdisciplinary Debate
- Tags: Physics general, Statistical Physics Dynamical Systems and Complexity, Control Robotics Mechatronics, Computing Methodologies, Philosophy, Evolutionary Biology
- Year: 2003
- Publisher: Springer-Verlag Berlin Heidelberg
- Edition: 1
- Language: English
- pdf
Adaptivity and learning have in recent decades become a common concern of scientific disciplines. These issues have arisen in mathematics, physics, biology, informatics, economics, and other fields more or less simultaneously. The aim of this publication is the interdisciplinary discourse on the phenomenon of learning and adaptivity. Different perspectives are presented and compared to find fruitful concepts for the disciplines involved. The authors select problems showing representative traits concerning the frame up, the methods and the achievements rather than to present extended overviews.
To foster interdisciplinary dialogue, this book presents diverse perspectives from various scientific fields, including:
- The biological perspective: e.g., physiology, behaviour;
- The mathematical perspective: e.g., algorithmic and stochastic learning;
- The physics perspective: e.g., learning for artificial neural networks;
- The "learning by experience" perspective: reinforcement learning, social learning, artificial life;
- The cognitive perspective: e.g., deductive/inductive procedures, learning and language learning as a high level cognitive process;
- The application perspective: e.g., robotics, control, knowledge engineering.
Adaptivity and learning have in recent decades become a common concern of scientific disciplines. These issues have arisen in mathematics, physics, biology, informatics, economics, and other fields more or less simultaneously. The aim of this publication is the interdisciplinary discourse on the phenomenon of learning and adaptivity. Different perspectives are presented and compared to find fruitful concepts for the disciplines involved. The authors select problems showing representative traits concerning the frame up, the methods and the achievements rather than to present extended overviews.
To foster interdisciplinary dialogue, this book presents diverse perspectives from various scientific fields, including:
- The biological perspective: e.g., physiology, behaviour;
- The mathematical perspective: e.g., algorithmic and stochastic learning;
- The physics perspective: e.g., learning for artificial neural networks;
- The "learning by experience" perspective: reinforcement learning, social learning, artificial life;
- The cognitive perspective: e.g., deductive/inductive procedures, learning and language learning as a high level cognitive process;
- The application perspective: e.g., robotics, control, knowledge engineering.
Adaptivity and learning have in recent decades become a common concern of scientific disciplines. These issues have arisen in mathematics, physics, biology, informatics, economics, and other fields more or less simultaneously. The aim of this publication is the interdisciplinary discourse on the phenomenon of learning and adaptivity. Different perspectives are presented and compared to find fruitful concepts for the disciplines involved. The authors select problems showing representative traits concerning the frame up, the methods and the achievements rather than to present extended overviews.
To foster interdisciplinary dialogue, this book presents diverse perspectives from various scientific fields, including:
- The biological perspective: e.g., physiology, behaviour;
- The mathematical perspective: e.g., algorithmic and stochastic learning;
- The physics perspective: e.g., learning for artificial neural networks;
- The "learning by experience" perspective: reinforcement learning, social learning, artificial life;
- The cognitive perspective: e.g., deductive/inductive procedures, learning and language learning as a high level cognitive process;
- The application perspective: e.g., robotics, control, knowledge engineering.
Content:
Front Matter....Pages I-XII
Adaptivity and Learning — an Interdisciplinary Debate....Pages 1-4
Front Matter....Pages 5-5
Biology of Adaptation and Learning....Pages 7-9
The Adaptive Properties of the Phosphate Uptake System of Cyanobacteria: Information Storage About Environmental Phosphate Supply....Pages 11-22
Cognitive Architecture of a Mini-Brain....Pages 23-48
Cerebral Mechanisms of Learning Revealed by Functional Neuroimaging in Humans....Pages 49-57
Creating Presence by Bridging Between the Past and the Future: the Role of Learning and Memory for the Organization of Life....Pages 59-70
Front Matter....Pages 71-71
The Physics Approach to Learning in Neural Networks....Pages 73-76
Statistical Physics of Learning and Generalization....Pages 77-88
The Statistical Physics of Learning: Phase Transitions and Dynamical Symmetry Breaking....Pages 89-99
The Complexity of Learning with Supportvector Machines — A Statistical Physics Study....Pages 101-108
Front Matter....Pages 109-109
Mathematics Approach to Learning....Pages 111-113
Learning and the Art of Fault-Tolerant Guesswork....Pages 115-140
Perspectives on Learning Symbolic Data with Connectionistic Systems....Pages 141-159
Statistical Learning and Kernel Methods....Pages 161-186
Inductive Versus Approximative Learning....Pages 187-209
Front Matter....Pages 211-211
Learning by Experience....Pages 213-215
Learning by Experience from Others — Social Learning and Imitation in Animals and Robots....Pages 217-241
Reinforcement Learning: a Brief Overview....Pages 243-264
A Simple Model for Learning from Unspecific Reinforcement....Pages 265-280
Front Matter....Pages 281-281
Aspects of Human-Like Cognition and AI Learning....Pages 283-284
Front Matter....Pages 281-281
Making Robots Learn to See....Pages 285-309
Using Machine Learning Techniques in Complex Multi-Agent Domains....Pages 311-328
Learning Similarities for Informally Defined Objects....Pages 329-345
Semiotic Cognitive Information Processing: Learning to Understand Discourse. A Systemic Model of Meaning Constitution....Pages 347-403
Adaptivity and learning have in recent decades become a common concern of scientific disciplines. These issues have arisen in mathematics, physics, biology, informatics, economics, and other fields more or less simultaneously. The aim of this publication is the interdisciplinary discourse on the phenomenon of learning and adaptivity. Different perspectives are presented and compared to find fruitful concepts for the disciplines involved. The authors select problems showing representative traits concerning the frame up, the methods and the achievements rather than to present extended overviews.
To foster interdisciplinary dialogue, this book presents diverse perspectives from various scientific fields, including:
- The biological perspective: e.g., physiology, behaviour;
- The mathematical perspective: e.g., algorithmic and stochastic learning;
- The physics perspective: e.g., learning for artificial neural networks;
- The "learning by experience" perspective: reinforcement learning, social learning, artificial life;
- The cognitive perspective: e.g., deductive/inductive procedures, learning and language learning as a high level cognitive process;
- The application perspective: e.g., robotics, control, knowledge engineering.
Content:
Front Matter....Pages I-XII
Adaptivity and Learning — an Interdisciplinary Debate....Pages 1-4
Front Matter....Pages 5-5
Biology of Adaptation and Learning....Pages 7-9
The Adaptive Properties of the Phosphate Uptake System of Cyanobacteria: Information Storage About Environmental Phosphate Supply....Pages 11-22
Cognitive Architecture of a Mini-Brain....Pages 23-48
Cerebral Mechanisms of Learning Revealed by Functional Neuroimaging in Humans....Pages 49-57
Creating Presence by Bridging Between the Past and the Future: the Role of Learning and Memory for the Organization of Life....Pages 59-70
Front Matter....Pages 71-71
The Physics Approach to Learning in Neural Networks....Pages 73-76
Statistical Physics of Learning and Generalization....Pages 77-88
The Statistical Physics of Learning: Phase Transitions and Dynamical Symmetry Breaking....Pages 89-99
The Complexity of Learning with Supportvector Machines — A Statistical Physics Study....Pages 101-108
Front Matter....Pages 109-109
Mathematics Approach to Learning....Pages 111-113
Learning and the Art of Fault-Tolerant Guesswork....Pages 115-140
Perspectives on Learning Symbolic Data with Connectionistic Systems....Pages 141-159
Statistical Learning and Kernel Methods....Pages 161-186
Inductive Versus Approximative Learning....Pages 187-209
Front Matter....Pages 211-211
Learning by Experience....Pages 213-215
Learning by Experience from Others — Social Learning and Imitation in Animals and Robots....Pages 217-241
Reinforcement Learning: a Brief Overview....Pages 243-264
A Simple Model for Learning from Unspecific Reinforcement....Pages 265-280
Front Matter....Pages 281-281
Aspects of Human-Like Cognition and AI Learning....Pages 283-284
Front Matter....Pages 281-281
Making Robots Learn to See....Pages 285-309
Using Machine Learning Techniques in Complex Multi-Agent Domains....Pages 311-328
Learning Similarities for Informally Defined Objects....Pages 329-345
Semiotic Cognitive Information Processing: Learning to Understand Discourse. A Systemic Model of Meaning Constitution....Pages 347-403
....