Jonathan Lawry – författare

Vague concepts are intrinsic to human communication. Somehow it would seems that vagueness is central to the flexibility and robustness of natural l- guage descriptions. If we were to insist on precise concept definitions then we would be able to assert very little with any degree of confidence. In many cases our perceptions simply do not provide sufficient information to allow us to verify that a set of formal conditions are met. Our decision to describe an individual as 'tall' is not generally based on any kind of accurate measurement of their height. Indeed it is part of the power of human concepts that they do not require us to make such fine judgements. They are robust to the imprecision of our perceptions, while still allowing us to convey useful, and sometimes vital, information. The study of vagueness in Artificial Intelligence (AI) is therefore motivated by the desire to incorporate this robustness and flexibility into int- ligent computer systems. This goal, however, requires a formal model of vague concepts that will allow us to quantify and manipulate the uncertainty resulting from their use as a means of passing information between autonomous agents. I first became interested in these issues while working with Jim Baldwin to develop a theory of the probability of fuzzy events based on mass assi- ments.

Vague concepts are intrinsic to human communication. Somehow it would seems that vagueness is central to the flexibility and robustness of natural l- guage descriptions. If we were to insist on precise concept definitions then we would be able to assert very little with any degree of confidence. In many cases our perceptions simply do not provide sufficient information to allow us to verify that a set of formal conditions are met. Our decision to describe an individual as ''tall'' is not generally based on any kind of accurate measurement of their height. Indeed it is part of the power of human concepts that they do not require us to make such fine judgements. They are robust to the imprecision of our perceptions, while still allowing us to convey useful, and sometimes vital, information. The study of vagueness in Artificial Intelligence (AI) is therefore motivated by the desire to incorporate this robustness and flexibility into int- ligent computer systems. This goal, however, requires a formal model of vague concepts that will allow us to quantify and manipulate the uncertainty resulting from their use as a means of passing information between autonomous agents. I first became interested in these issues while working with Jim Baldwin to develop a theory of the probability of fuzzy events based on mass assi- ments.

Vague concepts are intrinsic to human communication. Somehow it would seems that vagueness is central to the flexibility and robustness of natural l- guage descriptions. If we were to insist on precise concept definitions then we would be able to assert very little with any degree of confidence. In many cases our perceptions simply do not provide sufficient information to allow us to verify that a set of formal conditions are met. Our decision to describe an individual as 'tall' is not generally based on any kind of accurate measurement of their height. Indeed it is part of the power of human concepts that they do not require us to make such fine judgements. They are robust to the imprecision of our perceptions, while still allowing us to convey useful, and sometimes vital, information. The study of vagueness in Artificial Intelligence (AI) is therefore motivated by the desire to incorporate this robustness and flexibility into int- ligent computer systems. This goal, however, requires a formal model of vague concepts that will allow us to quantify and manipulate the uncertainty resulting from their use as a means of passing information between autonomous agents. I first became interested in these issues while working with Jim Baldwin to develop a theory of the probability of fuzzy events based on mass assi- ments.

Uncertainty in AI explores different theories of uncertainty as studied in the context of artificial intelligence. By adopting a common representation framework based on sets of possible worlds, it examines the relationships between different theories of uncertainty, taking note of the different properties that they satisfy, their expressiveness, and their computational complexity. It distinguishes between uncertainty about the true state of the world, ignorance about the correct level of uncertainty, and fuzziness in the propositions being evaluated. Concepts are introduced using simple illustrative examples, prioritising intuitive understanding before reviewing key mathematical results. This makes it ideal for undergraduate students looking to understand the strengths and weaknesses of different uncertainty formalisms, providing them with sufficient technical detail to begin to apply these tools in practice while requiring only foundation-level mathematics — as taught in the first year of most science and engineering undergraduate programmes.This book is based on material from "Uncertainty Modelling for Intelligent Systems", a course taught to third- and fourth-year undergraduate engineers and computer scientists at the University of Bristol for more than a decade. Instead of promoting a particular approach to or philosophy of uncertainty, these pages map the landscape of uncertainty theories, explicitly highlighting the connections and relationships between them that often remain implicit. It provides students with a broad overview, allowing them to better assess which uncertainty formalisms are most appropriate within the context of a particular application.

Uncertainty in AI explores different theories of uncertainty as studied in the context of artificial intelligence. By adopting a common representation framework based on sets of possible worlds, it examines the relationships between different theories of uncertainty, taking note of the different properties that they satisfy, their expressiveness, and their computational complexity. It distinguishes between uncertainty about the true state of the world, ignorance about the correct level of uncertainty, and fuzziness in the propositions being evaluated. Concepts are introduced using simple illustrative examples, prioritising intuitive understanding before reviewing key mathematical results. This makes it ideal for undergraduate students looking to understand the strengths and weaknesses of different uncertainty formalisms, providing them with sufficient technical detail to begin to apply these tools in practice while requiring only foundation-level mathematics — as taught in the first year of most science and engineering undergraduate programmes.This book is based on material from "Uncertainty Modelling for Intelligent Systems", a course taught to third- and fourth-year undergraduate engineers and computer scientists at the University of Bristol for more than a decade. Instead of promoting a particular approach to or philosophy of uncertainty, these pages map the landscape of uncertainty theories, explicitly highlighting the connections and relationships between them that often remain implicit. It provides students with a broad overview, allowing them to better assess which uncertainty formalisms are most appropriate within the context of a particular application.

Modelling with Words is an emerging modelling methodology closely related to the paradigm of Computing with Words introduced by Lotfi Zadeh.This book is an authoritative collection of key contributions to the new concept of Modelling with Words. A wide range of issues in systems modelling and analysis is presented, extending from conceptual graphs and fuzzy quantifiers to humanist computing and self-organizing maps. Among the core issues investigated are- balancing predictive accuracy and high level transparency in learning- scaling linguistic algorithms to high-dimensional data problems- integrating linguistic expert knowledge with knowledge derived from data- identifying sound and useful inference rules- integrating fuzzy and probabilistic uncertainty in data modelling

The analysis of experimental data resulting from some underlying random process is a fundamental part of most scientific research. Probability Theory and Statistics have been developed as flexible tools for this analyis, and have been applied successfully in various fields such as Biology, Economics, Engineering, Medicine or Psychology. However, traditional techniques in Probability and Statistics were devised to model only a singe source of uncertainty, namely randomness. In many real-life problems randomness arises in conjunction with other sources, making the development of additional "softening" approaches essential. This book is a collection of papers presented at the 2nd International Conference on Soft Methods in Probability and Statistics (SMPS’2004) held in Oviedo, providing a comprehensive overview of the innovative new research taking place within this emerging field.

The idea of soft computing emerged in the early 1990s from the fuzzy systems c- munity, and refers to an understanding that the uncertainty, imprecision and ig- rance present in a problem should be explicitly represented and possibly even - ploited rather than either eliminated or ignored in computations. For instance, Zadeh de?ned ‘Soft Computing’ as follows: Soft computing differs from conventional (hard) computing in that, unlike hard computing, it is tolerant of imprecision, uncertainty and partial truth. In effect, the role model for soft computing is the human mind. Recently soft computing has, to some extent, become synonymous with a hybrid approach combining AI techniques including fuzzy systems, neural networks, and biologically inspired methods such as genetic algorithms. Here, however, we adopt a more straightforward de?nition consistent with the original concept. Hence, soft methods are understood as those uncertainty formalisms not part of mainstream s- tistics and probability theory which have typically been developed within the AI and decisionanalysiscommunity.Thesearemathematicallysounduncertaintymodelling methodologies which are complementary to conventional statistics and probability theory.

The idea of soft computing emerged in the early 1990s from the fuzzy systems c- munity, and refers to an understanding that the uncertainty, imprecision and ig- rance present in a problem should be explicitly represented and possibly even - ploited rather than either eliminated or ignored in computations. For instance, Zadeh de?ned ‘Soft Computing’ as follows: Soft computing differs from conventional (hard) computing in that, unlike hard computing, it is tolerant of imprecision, uncertainty and partial truth. In effect, the role model for soft computing is the human mind. Recently soft computing has, to some extent, become synonymous with a hybrid approach combining AI techniques including fuzzy systems, neural networks, and biologically inspired methods such as genetic algorithms. Here, however, we adopt a more straightforward de?nition consistent with the original concept. Hence, soft methods are understood as those uncertainty formalisms not part of mainstream s- tistics and probability theory which have typically been developed within the AI and decisionanalysiscommunity.Thesearemathematicallysounduncertaintymodelling methodologies which are complementary to conventional statistics and probability theory.

Large-scale data processing is important. Most successful applications of m- ern science and engineering, from discovering the human genome to predicting weather to controlling space missions, involve processing large amounts of data and large knowledge bases. The corresponding large-scale data and knowledge processing requires intensive use of computers. Computers are based on processing exact data values and truth values from the traditional 2-value logic. The ability of computers to perform fast data and knowledgeprocessingisbasedonthehardwaresupportforsuper-fastelementary computer operations, such as performing arithmetic operations with (exactly known) numbers and performing logical operations with binary (“true”-“false”) logical values. In practice, we need to go beyond exact data values and truth values from the traditional 2-value logic. In practical applications, we need to go beyond such operations. Input is only known with uncertainty. Let us ?rst illustrate this need on the example of operations with numbers. Hardware-supported computer operations (implicitly) assume that we know the exact values of the input quantities. In reality, the input data usually comes from measurements. Measurements are never 100% accurate. Due to such factors as imperfection of measurement - struments and impossibility to reduce noise level to 0, the measured value x of each input quantity is, in general, di?erent from the (unknown) actual value x of this quantity. It is therefore necessary to ?nd out how this input uncertainty def ?x = x ?x = 0 a?ects the results of data processing.

Solving practical problems often requires the integration of information and knowledge from many different sources, taking into account uncertainty and impreciseness. The 2010 International Symposium on Integrated Uncertainty Management and Applications (IUM’2010), which takes place at the Japan Advanced Institute of Science and Technology (JAIST), Ishikawa, Japan, between 9th–11th April, is therefore conceived as a forum for the discussion and exchange of research results, ideas for and experience of application among researchers and practitioners involved with all aspects of uncertainty modelling and management.

Solving practical problems often requires the integration of information and knowledge from many different sources, taking into account uncertainty and impreciseness. The 2010 International Symposium on Integrated Uncertainty Management and Applications (IUM’2010), which takes place at the Japan Advanced Institute of Science and Technology (JAIST), Ishikawa, Japan, between 9th–11th April, is therefore conceived as a forum for the discussion and exchange of research results, ideas for and experience of application among researchers and practitioners involved with all aspects of uncertainty modelling and management.

This book constitutes the refereed proceedings of the International Symposium on Integrated Uncertainty in Knowledge Modeling and Decision Making, IUKM 2011, held in Hangzhou, China, in October 2011. The 21 revised full papers presented together with 1 keynote lecture and 5 invited talks were carefully reviewed and selected from 55 submissions. The papers provide a wealth of new ideas and report both theoretical and applied research on integrated uncertainty modeling and management.