Bruce Edmonds

Bio: Bruce Edmonds is an academic researcher from Manchester Metropolitan University. The author has contributed to research in topics: Social simulation & Context (language use). The author has an hindex of 38, co-authored 191 publications receiving 5368 citations. Previous affiliations of Bruce Edmonds include University of Los Andes.

The ODD protocol for describing agent-based and other simulation models: A second update to improve clarity, replication, and structural realism

Abstract: The Overview, Design concepts and Details (ODD) protocol for describing Individual-and Agent-Based Models (ABMs) is now widely accepted and used to document such models in journal articles. As a standardized document for providing a consistent, logical and readable account of the structure and dynamics of ABMs, some research groups also find it useful as a workflow for model design. Even so, there are still limitations to ODD that obstruct its more widespread adoption. Such limitations are discussed and addressed in this paper: the limited availability of guidance on how to use ODD; the length of ODD documents; limitations of ODD for highly complex models; lack of sufficient details of many ODDs to enable reimplementation without access to the model code; and the lack of provision for sections in the document structure covering model design ratio-nale, the model’s underlying narrative, and the means by which the model’s fitness for purpose is evaluated. We document the steps we have taken to provide better guidance on: structuring complex ODDs and an ODD summary for inclusion in a journal article (with full details in supplementary material; Table 1); using ODD to point readers to relevant sections of the model code; update the document structure to include sections on model rationale and evaluation. We also further advocate the need for standard descriptions of simulation experiments and argue that ODD can in principle be used for any type of simulation model. Thereby ODD would provide a lingua franca for simulation modelling.

From KISS to KIDS: an 'anti-simplistic' modelling approach

Abstract: A new approach is suggested under the slogan “Keep it Descriptive Stupid” (KIDS) that encapsulates a trend in increasingly descriptive agent-based social simulation. The KIDS approach entails one starts with the simulation model that relates to the target phenomena in the most straight-forward way possible, taking into account the widest possible range of evidence, including anecdotal accounts and expert opinion. Simplification is only applied if and when the model and evidence justify this. This contrasts sharply with the KISS approach where one starts with the simplest possible model and only moves to a more complex one if forced to. An example multi-agent simulation of domestic water demand and social influence is described.

Socially Intelligent Agents: Creating Relationships With Computers And Robots

Abstract: The field of Socially Intelligent Agents (SIA) is a fast growing and increasingly important area that comprises highly active research activities and strongly interdisciplinary approaches. Socially Intelligent Agents, edited by Kerstin Dautenhahn, Alan Bond, Lola Caamero and Bruce Edmonds, emerged from the AAAI Symposium "Socially Intelligent Agents - The Human in the Loop". The book provides 32 chapters, written by leading SIA researchers, addressing topics such as: social robotics, embodied conversational agents, affective computing, anthropomorphism, narrative and story-telling, social aspects in multi-agent systems, new technologies for education and therapy, and more. This breadth of topics covered in Socially Intelligent Agents provides the reader with a comprehensive look at current research activities in the area. Socially Intelligent Agents serves as an excellent reference for a wide readership, e.g. computer scientists, roboticists, web programmers and designers, computer users, cognitive scientists, and other researchers interested in the study of how humans relate to computers and robots, and how these agents in return can relate to humans. This book is also suitable as research material in a variety of advanced level courses, including Applied Artificial Intelligence, Autonomous Agents, Human-Computer Interaction, Situated, Embodied AI.

Syntactic Measures of Complexity

Abstract: page 14 Declaration page 15 Notes of copyright and the ownership of intellectual property rights page 15 The Author page 16 Acknowledgements page 16 1 Introduction page 17 1.1 Background page 17 1.2 The Style of Approach page 18 1.3 Motivation page 19 1.4 Style of Presentation page 20 1.5 Outline of the Thesis page 21 2 Models and Modelling page 23 2.1 Some Types of Models page 25 2.2 Combinations of Models page 28 2.3 Parts of the Modelling Apparatus page 33 2.4 Models in Machine Learning page 38 2.5 The Philosophical Background to the Rest of this Thesis page 41 Syntactic Measures of Complexity page 3 3 Problems and Properties page 44 3.1 Examples of Common Usage page 44 3.1.1 A case of nails page 44 3.1.2 Writing a thesis page 44 3.1.3 Mathematics page 44 3.1.4 A gas page 44 3.1.5 An ant hill page 45 3.1.6 A car engine page 45 3.1.7 A cell as part of an organism page 46 3.1.8 Computer programming page 46 3.2 Complexity as a Comparison page 46 3.2.1 The emergence of life page 47 3.3 What the Property of Complexity Could Usefully Refer to page 47 3.3.1 Natural systems page 47 3.3.2 The interaction of an observer with a system page 53 3.3.3 Patterns page 55 3.3.4 The modelling relation page 56 3.3.5 A model with respect to a specified framework page 56 3.4 Some Unsatisfactory Accounts of Complexity page 57 3.4.1 Size page 57 3.4.2 Size of rules page 58 3.4.3 Minimal size page 58 3.4.4 Processing time page 59 3.4.5 Ignorance page 60 3.4.6 Variety page 61 3.4.7 Midpoint between order and disorder page 62 3.4.8 Improbability page 63 3.4.9 Expressivity page 65 3.4.10 Dimension page 65 3.4.11 Ability to surprise page 66 3.4.12 Logical strength page 66 Syntactic Measures of Complexity page 4 3.4.13 Irreducibility page 67 3.5 Complexity is Relative to the Frame of Reference page 68 3.5.1 The level of application page 68 3.5.2 Goals type of difficulty page 69 3.5.3 Atomic parts page 69 3.5.4 The language of description page 69 4 A Definition of Complexity page 72 4.1 Aspects of the Definition page 75 4.1.1 Identity of a system page 75 4.1.2 Atomic components page 76 4.1.3 Difficulty page 77 4.1.4 Formulating overall behaviour page 78 4.1.5 Complexity vs. ignorance page 79 4.1.6 As a gap between the global and local page 80 4.1.7 The comparative nature of complexity page 80 4.1.8 The existence of complexity page 81 4.1.9 Relativisation to a language page 81 4.2 Examples page 81 4.2.1 The flight behaviour of a herd page 82 4.2.2 Cellular automata page 82 4.3 Relationship to Some Other Formulations page 83 4.3.1 Number of inequivalent descriptions page 83 4.3.2 Effective measure complexity page 84 4.3.3 Computational complexity page 84 4.3.4 Algorithmic information complexity page 84 4.3.5 Shannon entropy page 85 4.3.6 Crutchfield’s “topological complexity” page 85 5 Applications of Complexity to Formal Languages page 86 5.1 Types of Complexity Involving Formal Languages page 86 5.2 Expected Properties of “Analytic Complexity” page 87 Syntactic Measures of Complexity page 5 5.2.1 Independent of the particular symbols used page 87 5.2.2 The complexity of sub-expressions should be less than the whole page 87 5.2.3 Expressions with no repetitions are simple page 88 5.2.4 Small size should limit the possible complexity page 89 5.2.5 There should be no upper limit to complexity if the language is suitably generative page 89 5.2.6 The complexity of irrelevant substitutions page 90 5.2.7 The complexity of relevant relating of expressions page 91 5.2.8 Decomposability of expressions page 91 5.3 Measures of Analytic Complexity page 93 5.3.1 Notation page 93 5.3.2 Weak complexity measures page 95 5.3.3 Weak complexity measures where simple repetition does not increase complexity page 100 5.3.4 Weak complexity measures that respect the subformula relation and where simple repetition does not increase complexity page 102 5.3.5 Strong complexity measures page 104 5.4 The Cyclomatic Number as a Measure of Analytic Complexity page 106 5.5 Layers of Syntax and Complexity page 108 5.5.1 Example 1 a supply of variable names page 109 5.5.2 Example 2 WFFs of the implication fragment page 110 5.5.3 Example 3 The implicational fragment of E page 111 5.5.4 Discussion of syntactic structures page 112 5.6 Application to Axioms and Proof Systems page 113 5.6.1 Axiom complexity page 113 5.6.2 Proof complexity page 117 5.7 Application to Simplification page 120 5.7.1 Searching over equivalent expressions within a language page 120 5.7.2 Searching over equivalent derivations within a language page 121 5.7.3 Specialising the syntactic level page 121 Syntactic Measures of Complexity page 6 5.7.4 Searching over equivalent languages page 123 5.7.5 Simplification via trade-offs with specificity and accuracy page 124 6 Philosophical Applications page 126 6.1 Complexity and Relevance page 126 6.2 Complexity and Emergence page 126 6.3 Complexity and Language page 128 6.4 Complexity and Representation page 128 6.5 Complexity and “Simplicity” page 129 6.6 Complexity and Evolution page 130 6.7 Complexity and Holism page 131 6.8 Complexity and System Identity page 132 6.9 Complexity and Society page 133 7 Conclusion page 134 7.1 Further Work page 134 8 Appendix 1 A Brief Overview of Some Existing Formulations of Complexity page 136 8.1 Abstract Computational Complexity page 136 8.2 Algorithmic Information Complexity page 136 8.3 Arithmetic Complexity page 138 8.4 Bennett's ‘Logical Depth’ page 138 8.5 Cognitive Complexity page 139 8.6 Connectivity page 140 8.7 Cyclomatic Number page 140 8.8 Descriptive/Interpretative Complexity page 141 8.9 Dimension of Attractor page 141 8.10 Ease of Decomposition page 142 8.11 Economic Complexity page 142 Syntactic Measures of Complexity page 7 8.12 Entropy page 143 8.13 Goodman's Complexity page 143 8.14 Horn Complexity page 143 8.15 Information page 144 8.16 Information Gain in Hierarchically Approximation and Scaling page 145 8.17 Irreducibility page 145 8.18 Kemeny's Complexity page 146 8.19 Length of Proof page 146 8.20 Logical Complexity/Arithmetic Hierarchy page 146 8.21 Loop Complexity page 147 8.22 Low Probability page 148 8.23 Minimum Number of Sub Groups page 148 8.24 Minimum Size page 149 8.25 Mutual Information page 151 8.26 Network Complexity page 151 8.27 Number of Axioms page 152 8.28 Number of Dimensions page 152 8.29 Number of Inequivalent Descriptions page 152 8.30 Number of Internal Relations page 153 8.31 Number of Spanning Trees page 153 8.32 Number of States in a Finite Automata page 153 8.33 Number of Symbols page 154 8.34 Number of Variables page 155 8.35 Organised/Disorganised Complexity page 155 8.36 Shannon Information page 156 8.37 Simplicity page 156 8.38 Size page 157 Syntactic Measures of Complexity page 8 8.39 Size of Grammar page 157 8.40 Size of matrix page 158 8.41 Sober's Minimum Extra Information page 158 8.42 Sophistication page 159 8.43 Stochastic Complexity page 160 8.44 Syntactic Depth page 160 8.45 Tabular Complexity page 161 8.46 Thermodynamic Depth page 161 8.47 Time and Space Computational Complexity page 162 8.48 Variety page 163 9 Appendix 2 Longer Proofs page 164 9.1 (Non-existence of) Complexity Measures on Strings page 164 9.2 Cyclomatic Number as a Lower Bound for Minimal Damage Cut page 169 9.3 Decomposition of Formulas into Complexes page 169 9.4 Generating a Measure from a Function on the Complexes page 170 9.5 Three Conditions that are Equivalent on a Weak Complexity Measure page 175 10 Appendix 3 Formalisation of Syntactic Structure page 182 10.1 Formalisation page 182 10.1.1 The syntax of trees page 182 10.1.2 The syntax of rules page 182 10.1.3 The syntax of syntactic structures: page 182 10.1.4 Generation from syntactic structures page 183 10.1.5 Production from trees page 183 10.1.6 Complete production page 184 10.1.7 Complete productive generation from syntactic structures page 184 10.2 The Expressivity of Syntactic Structures page 184 10.3 Flattening Syntactic Structures page 187 Syntactic Measures of Complexity page 9 11 Appendix 4 A tool for exploring syntactic structures, complexity and simplification page 188 11.1 Overview page 188 11.2 Examples page 188 11.3 Programming page 190 11.4 Interface page 192 12 Appendix 5 A comparison of different rankings of logical formula page 193 13 Appendix 6 Complexity and Scientific Modelling page 199 Overview page 199 Complexity page 200 A Framework for Analysing Modelling page 201 Other Formulations of Complexity page 202 Order and Disorder page 203 Noise page 206 Complexity vs. Information page 207 Complexity and Induction page 207 Conclusion page 208 14 Appendix 7 Complexity and Economics page 210 What is Complexity? page 210 “Complexity” in economics page 210 The “Sciences of Complexity” page 210 Complexityper se page 211 The effects of complexity on modelling by agents page 213 Ideal rationality and perfect information page 213 Ideal rationality and noisy information page 213 Ideal rationality and inadequate information page 214 Bounded rationality and inadequate information page 214 The effects of modelling by agents on complexity page 215 Syntactic Measures of Complexity page 10 Ignoring the process of modelling by economic agents page 215 Including the process of modelling by economic agents page 215 Towards dealing with the complexity of modelling agents modelling modelling page 217 The Form meaning distinction page 217 The complexity, specificity, error trade-off page 218 The modelling language page 219 Processes of model development page 219 Some future directions for economic modelling page 220 Applying our model of modelling to ourselves page 220 Relatively new (non-numerical) techniques page 221 Conclusion complexity again page 222 15 References page 223 Syntactic Measures of Complexity page 11 List of Figures Figure 1: Entity, W, using A as a model of B page 24 Figure 2: An illustration of the syntactic view of models page 28 Figure 3: A semantic picture of modelling (from Giere in [176]) page 29 Figure 4: T

Sociology and simulation : Statistical and qualitative cross-validation

Abstract: Agent‐based simulation modeling enables the construction of formal models that simultaneously can be microvalidated against accounts of individual behavior and macrovalidated against aggregate data that show the characteristics of many socially derived time series These characteristics (leptokurtosis and clustered volatility) have two important consequences: first, they also appear in suitably structured agent‐based models where, like real social actors, agents are socially embedded and metastable; second, their presence precludes the use of many standard statistical techniques like the chi‐square test These characteristics in time‐series data indicate that a suitable agent‐based model rather than a standard statistical model will be appropriate This is illustrated with an agent‐based model of mutual social influence on domestic water demand The consequences for many frequently used statistical techniques are discussed

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Statistical physics of social dynamics

Abstract: Statistical physics has proven to be a fruitful framework to describe phenomena outside the realm of traditional physics. Recent years have witnessed an attempt by physicists to study collective phenomena emerging from the interactions of individuals as elementary units in social structures. A wide list of topics are reviewed ranging from opinion and cultural and language dynamics to crowd behavior, hierarchy formation, human dynamics, and social spreading. The connections between these problems and other, more traditional, topics of statistical physics are highlighted. Comparison of model results with empirical data from social systems are also emphasized.