One of a small number of books that try to give a constructive explanation of intelligence/cognition/thinking as a whole
A novel and original approach that challenges all dominating theories
Theoretical discussions combined with design details
Unified solutions to many traditional problems in several fields (artificial intelligence, logic, psychology, philosophy, linguistics, ...)
This book is the most comprehensive deillegalscription of the decades-long Non-Axiomatic Reasoning System (NARS) project, including its philosophical foundation, methodological consideration, conceptual design details, implications in the related fields, and its similarities and differences to many related works in cognitive science. While most current works in Artificial Intelligence (AI) focus on individual aspects of intelligence and cognition, NARS is designed and developed to attack the AI problem as a whole.
Preface Acknowledgment PART I. Theoretical Foundation Chapter 1. The Goal of Artificial Intelligence 1.1 To define intelligence 1.2 Various schools in AI research 1.3 AI as a whole Chapter 2. A New Approach Toward AI 2.1 To define AI 2.2 Intelligent reasoning systems 2.3 Major design issues of NARS PART II. Non-Axiomatic Reasoning System Chapter 3. The Core Logic 3.1 NAL-0: binary inheritance 3.2 The language of NAL-1 3.3 The inference rules of NAL-1 Chapter 4. First-Order Inference 4.1 Compound terms 4.2 NAL-2: sets and variants of inheritance 4.3 NAL-3: intersections and differences 4.4 NAL-4: products, images, and ordinary relations Chapter 5. Higher-Order Inference 5.1 NAL-5: statements as terms 5.2 NAL-6: statements with variables 5.3 NAL-7: temporal statements 5.4 NAL-8: procedural statements Chapter 6. Inference Control 6.1 Task management 6.2 Memory structure 6.3 Inference processes 6.4 Budget assessment . PART III. Comparison and Discussion Chapter 7. Semantics 7.1 Experience vs. model 7.2 Extension and intension 7.3 Meaning of term 7.4 Truth of statement Chapter 8. Uncertainty 8.1 The non-numerical approaches 8.2 The fuzzy approach 8.3 The Bayesian approach 8.4 Other probabilistic approaches 8.5 Unified representation of uncertainty Chapter 9. Inference Rules 9.1 Deduction 9.2 Induction 9.3 Abduction 9.4 Implication Chapter 10. NAL as a Logic 10.1 NAL as a term logic 10.2 NAL vs. predicate logic 10.3 Logic and AI Chapter 11. Categorization and Learning 11.1 Concept and categorization 11.2 Learning in NARS Chapter 12. Control and Computation 12.1 NARS and theoretical computer science 12.2 Various assumptions about resources 12.3 Dynamic natures of NARS PART IV. Conclusions Chapter 13. Current Results 13.1 Theoretical foundation 13.2 Formal model 13.3 Computer implementation Chapter 14. NARS in the Future 14.1 Next steps of the project 14.2 What NARS is not 14.3 General implications Bibliography Index
This book provides the blueprint of a thinking machine.
While most of the current works in Artificial Intelligence (AI) focus on individual aspects of intelligence and cognition, the project described in this book, Non-Axiomatic Reasoning System (NARS), is designed and developed to attack the AI problem as a whole.
This project is based on the belief that what we call "intelligence" can be understood and reproduced as "the capability of a system to adapt to its environment while working with insufficient knowledge and resources". According to this idea, a novel reasoning system is designed, which challenges all the dominating theories in how such a system should be built. The system carries out reasoning, learning, categorizing, planning, decision making, etc., as different facets of the same underlying process. This theory also provides unified solutions to many problems in AI, logic, psychology, and philosophy.
This book is the most comprehensive deillegalscription of this decades-long project, including its philosophical foundation, methodological consideration, conceptual design details, its implications in the related fields, as well as its similarities and differences to many related works in cognitive sciences.
From the reviews:
"Rigid Flexibility presents a new theory of cognition. As such it is devoted to the general research for Artificial Intelligence (AI), in contrast to a focus of other AI research that is focusing on solving specific reasoning problems such as planning or learning for example. ... The review of the principles and assumptions underlying the various streams of AI research make this book very interesting to read and enable the reader to easily compare the presented theory with other existing approaches." (Jana Koehler, Zentralblatt MATH, Vol. 1122 (24), 2007)
Theoretical Foundation.- The Goal of Artificial Intelligence.- A New Approach Toward AI.- Non-Axiomatic Reasoning System.- The Core Logic.- First-Order Inference.- Higher-Order Inference.- Inference Control.- Comparison and Discussion.- Semantics.- Uncertainty.- Inference Rules.- NAL as a Logic.- Categorization and Learning.- Control and Computation.- Conclusions.- Current Results.- NARS in the Future.
From the reviews:
"Rigid Flexibility presents a new theory of cognition. As such it is devoted to the general research for Artificial Intelligence (AI), in contrast to a focus of other AI research that is focusing on solving specific reasoning problems such as planning or learning for example. ... The review of the principles and assumptions underlying the various streams of AI research make this book very interesting to read and enable the reader to easily compare the presented theory with other existing approaches." (Jana Koehler, Zentralblatt MATH, Vol. 1122 (24), 2007)
Inhaltsverzeichnis
Preface Acknowledgment PART I. Theoretical Foundation Chapter 1. The Goal of Artificial Intelligence 1.1 To define intelligence 1.2 Various schools in AI research 1.3 AI as a whole Chapter 2. A New Approach Toward AI 2.1 To define AI 2.2 Intelligent reasoning systems 2.3 Major design issues of NARS PART II. Non-Axiomatic Reasoning System Chapter 3. The Core Logic 3.1 NAL-0: binary inheritance 3.2 The language of NAL-1 3.3 The inference rules of NAL-1 Chapter 4. First-Order Inference 4.1 Compound terms 4.2 NAL-2: sets and variants of inheritance 4.3 NAL-3: intersections and differences 4.4 NAL-4: products, images, and ordinary relations Chapter 5. Higher-Order Inference 5.1 NAL-5: statements as terms 5.2 NAL-6: statements with variables 5.3 NAL-7: temporal statements 5.4 NAL-8: procedural statements Chapter 6. Inference Control 6.1 Task management 6.2 Memory structure 6.3 Inference processes 6.4 Budget assessment . PART III. Comparison and Discussion Chapter 7. Semantics 7.1 Experience vs. model 7.2 Extension and intension 7.3 Meaning of term 7.4 Truth of statement Chapter 8. Uncertainty 8.1 The non-numerical approaches 8.2 The fuzzy approach 8.3 The Bayesian approach 8.4 Other probabilistic approaches 8.5 Unified representation of uncertainty Chapter 9. Inference Rules 9.1 Deduction 9.2 Induction 9.3 Abduction 9.4 Implication Chapter 10. NAL as a Logic 10.1 NAL as a term logic 10.2 NAL vs. predicate logic 10.3 Logic and AI Chapter 11. Categorization and Learning 11.1 Concept and categorization 11.2 Learning in NARS Chapter 12. Control and Computation 12.1 NARS and theoretical computer science 12.2 Various assumptions about resources 12.3 Dynamic natures of NARS PART IV. Conclusions Chapter 13. Current Results 13.1 Theoretical foundation 13.2 Formal model 13.3 Computer implementation Chapter 14. NARS in the Future 14.1 Next steps of the project 14.2 What NARS is not 14.3 General implications Bibliography Index
Klappentext
This book is the most comprehensive deillegalscription of the decades-long Non-Axiomatic Reasoning System (NARS) project, including its philosophical foundation, methodological consideration, conceptual design details, implications in the related fields, and its similarities and differences to many related works in cognitive science. While most current works in Artificial Intelligence (AI) focus on individual aspects of intelligence and cognition, NARS is designed and developed to attack the AI problem as a whole.
One of a small number of books that try to give a constructive explanation of intelligence/cognition/thinking as a whole
A novel and original approach that challenges all dominating theories
Theoretical discussions combined with design details
Unified solutions to many traditional problems in several fields (artificial intelligence, logic, psychology, philosophy, linguistics, ...)
