Melanie Mitchell | Portland State University (original) (raw)

Papers by Melanie Mitchell

Abstract How does an evolutionary process interact with a decentralized, distributed system in or... more Abstract How does an evolutionary process interact with a decentralized, distributed system in order to produce globally coordinated behavior? Using a genetic algorithm (GA) to evolve cellular automata (CAs), we show that the evolution of spontaneous synchronization, one type of emergent coordination, takes advantage of the underlying medium's potential to form embedded particles. The particles, typically phase defects between synchronous regions, are designed by the evolutionary process to resolve frustrations in the global phase.

Abstract Coevolution, between a population of candidate solutions and a population of test cases,... more Abstract Coevolution, between a population of candidate solutions and a population of test cases, has received increasing attention as a promising biologically inspired method for improving the performance of evolutionary computation techniques. However, the results of studies of coevolution have been mixed. One of the seemingly more impressive results to date was the improvement via coevolution demonstrated by Juille and Pollack (1998) on evolving cellular automata to perform a classification task.

Abstract We review recent work done by our group on applying genetic algorithms (GAs) to the desi... more Abstract We review recent work done by our group on applying genetic algorithms (GAs) to the design of cellular automata (CAs) that can perform computations requiring global coordination. A GA was used to evolve CAs for two computational tasks: density classification and synchronization. In both cases, the GA discovered rules that gave rise to sophisticated emergent computational strategies.

Abstract. Metastability is a common phenomenon. Many evolutionary processes, both natural and art... more Abstract. Metastability is a common phenomenon. Many evolutionary processes, both natural and artificial, alternate between periods of stasis and brief periods of rapid change in their behavior. In this paper an analytical model for the dynamics of a mutationonly genetic algorithm (GA) is introduced that identifies a new and general mechanism causing metastability in evolutionary dynamics. The GA's population dynamics is described in terms of flows in the space of fitness distributions.

ABSTRACT A genetic algorithm (GA) for automating the segmentation of the prostate on pelvic compu... more ABSTRACT A genetic algorithm (GA) for automating the segmentation of the prostate on pelvic computed tomography (CT) images is presented here. The images consist of slices from three-dimensional CT scans. Segmentation is typically performed manually on these images for treatment planning by an expert physician, who uses the “learned” knowledge of organ shapes, textures and locations to draw a contour around the prostate.

Mimicking biological evolution and harnessing its optimization power are problems that have intri... more Mimicking biological evolution and harnessing its optimization power are problems that have intrigued computer scientists for at least three decades. Genetic algorithms (GAs), invented by John Holland in the 1960s, are the most widely used approaches to computational evolution. In his book Adaptation in Natural and Arti cial Systems (Holland, 1975/1992, also reviewed in this issue), Holland presented GAs in a general theoretical framework for adaptation in nature.

abstract We describe the implementation and performance of a genetic algorithm which generates im... more abstract We describe the implementation and performance of a genetic algorithm which generates image feature extraction algorithms for remote sensing applications. We describe our basis set of primitive image operators and present our chromosomal representation of a complete algorithm. Our initial application has been geospatial feature extraction using publicly available multi-spectral aerial-photography data sets.

Analogy Making as a Complex Adaptive System Melanie Mitchell 1 INTRODUCTION This chapter describe... more Analogy Making as a Complex Adaptive System Melanie Mitchell 1 INTRODUCTION This chapter describes a computer program, called Copycat, that models how people make analogies. It might seem odd to include such a topic in a collection of chapters mostly on the immune system.

Identifying a shape's components can be essential for object recognition, object completion, and ... more Identifying a shape's components can be essential for object recognition, object completion, and shape matching, among other computer vision tasks [1]. In this paper we present a novel shape-decomposition algorithm, aimed at capturing some of the heuristics used by humans when parsing shapes. In 1984, Hoffman and Richards [2] proposed the minima rule, a simple heuristic for making straight-line cuts that decompose a given shape (or silhouette): Given a silhouette such as the one in Fig.

Science arises from the very human desire to understand and control the world. Over the course of... more Science arises from the very human desire to understand and control the world. Over the course of history, we humans have gradually built up a grand edifice of knowledge that enables us to predict, to varying extents, the weather, the motions of the planets, solar and lunar eclipses, the courses of diseases, the rise and fall of economic growth, the stages of language development in children, and a vast panorama of other natural, social, and cultural phenomena.

In our work we are studying how genetic algorithms (GAs) can evolve cellular automata (CAs) to pe... more In our work we are studying how genetic algorithms (GAs) can evolve cellular automata (CAs) to perform computations that require global coordination. The “evolving cellular automata” framework is an idealized means for studying how evolution (natural or computational) can create systems that perform emergent computation, in which the actions of simple components with local information and communication give rise to coordinated global information processing [3].

ABSTRACT A micro-world is described, in which many analogies involving strikingly different conce... more ABSTRACT A micro-world is described, in which many analogies involving strikingly different concepts and levels of subtlety can be made. The question" What differentiates the good ones from the bad ones?" is discussed, and then the problem of how to implement a computational model of the human ability to come up with such analogies (and to have a sense for their quality) is considered.

Abstract The building-block hypothesis states that the GA works well when short, low-order, highl... more Abstract The building-block hypothesis states that the GA works well when short, low-order, highly-fit schemas recombine to form even more highly fit higher-order schemas. The ability to produce fitter and fitter partial solutions by combining building blocks is believed to be a primary source of the GA's search power, but the GA research community currently lacks precise and quantitative descriptions of how schema processing actually takes place during the typical evolution of a GA search.

Abstract How can self-awareness emerge in a distributed system with no central control? How can s... more Abstract How can self-awareness emerge in a distributed system with no central control? How can such awareness feed back in a decentralized way to control the system's behavior? Many people have written about how selfawareness might come about in the brain. In this paper, I examine mechanisms for self-awareness and control in two other decentralized biological systems: the immune system and ant colonies. I then attempt to isolate some principles common to both systems.

In this article, the term biological computation refers to the proposal that living organisms the... more In this article, the term biological computation refers to the proposal that living organisms themselves perform computations, and, more specifically, that the abstract ideas of information and computation may be key to understanding biology in a more unified manner. It is important to point out that the study of biological computation is typically not the focus of the field of computational biology, which applies computing tools to the solution of specific biological problems.

What enables individually simple insects like ants to act with such precision and purpose as a gr... more What enables individually simple insects like ants to act with such precision and purpose as a group? How do trillions of individual neurons produce something as extraordinarily complex as consciousness? What is it that guides self-organizing structures like the immune system, the World Wide Web, the global economy, and the human genome? These are just a few of the fascinating and elusive questions that the science of complexity seeks to answer.

Abstract We present results from experiments in which a genetic algorithm (GA) was used to evolve... more Abstract We present results from experiments in which a genetic algorithm (GA) was used to evolve cellular automata (CAs) to perform a particular computational task-one-dimensional density classification. We look in detail at the evolutionary mechanisms producing the GA's behavior on this task and the impediments faced by the GA.

Abstract A simple evolutionary process can discover sophisticated methods for emergent informatio... more Abstract A simple evolutionary process can discover sophisticated methods for emergent information processing in decentralized spatially extended systems. The mechanisms underlying the resulting emergent computation are explicated by a technique for analyzing particle-based logic embedded in pattern-forming systems.

Abstract Genetic algorithms (GAs) play a major role in many artificial-life systems, but there is... more Abstract Genetic algorithms (GAs) play a major role in many artificial-life systems, but there is often little detailed understanding of why the GA performs as it does, and little theoretical basis on which to characterize the types of fitness landscapes that lead to successful GA performance. In this paper we propose a strategy for addressing these issues.

We present results from experiments in which a genetic algorithm (GA) is used to evolve 2D cellul... more We present results from experiments in which a genetic algorithm (GA) is used to evolve 2D cellular automata (CA) to perform a particular computational task (“density classification”) that requires globally coordinated information processing. The results are similar to that of earlier work on evolving 1D CAs. The behavior of the evolved 2D CAs is analyzed, and their performance is compared with that of several hand-designed 2D CAs.

Abstract How does an evolutionary process interact with a decentralized, distributed system in or... more Abstract How does an evolutionary process interact with a decentralized, distributed system in order to produce globally coordinated behavior? Using a genetic algorithm (GA) to evolve cellular automata (CAs), we show that the evolution of spontaneous synchronization, one type of emergent coordination, takes advantage of the underlying medium's potential to form embedded particles. The particles, typically phase defects between synchronous regions, are designed by the evolutionary process to resolve frustrations in the global phase.

Abstract Coevolution, between a population of candidate solutions and a population of test cases,... more Abstract Coevolution, between a population of candidate solutions and a population of test cases, has received increasing attention as a promising biologically inspired method for improving the performance of evolutionary computation techniques. However, the results of studies of coevolution have been mixed. One of the seemingly more impressive results to date was the improvement via coevolution demonstrated by Juille and Pollack (1998) on evolving cellular automata to perform a classification task.

Abstract We review recent work done by our group on applying genetic algorithms (GAs) to the desi... more Abstract We review recent work done by our group on applying genetic algorithms (GAs) to the design of cellular automata (CAs) that can perform computations requiring global coordination. A GA was used to evolve CAs for two computational tasks: density classification and synchronization. In both cases, the GA discovered rules that gave rise to sophisticated emergent computational strategies.

Abstract. Metastability is a common phenomenon. Many evolutionary processes, both natural and art... more Abstract. Metastability is a common phenomenon. Many evolutionary processes, both natural and artificial, alternate between periods of stasis and brief periods of rapid change in their behavior. In this paper an analytical model for the dynamics of a mutationonly genetic algorithm (GA) is introduced that identifies a new and general mechanism causing metastability in evolutionary dynamics. The GA's population dynamics is described in terms of flows in the space of fitness distributions.

ABSTRACT A genetic algorithm (GA) for automating the segmentation of the prostate on pelvic compu... more ABSTRACT A genetic algorithm (GA) for automating the segmentation of the prostate on pelvic computed tomography (CT) images is presented here. The images consist of slices from three-dimensional CT scans. Segmentation is typically performed manually on these images for treatment planning by an expert physician, who uses the “learned” knowledge of organ shapes, textures and locations to draw a contour around the prostate.

Mimicking biological evolution and harnessing its optimization power are problems that have intri... more Mimicking biological evolution and harnessing its optimization power are problems that have intrigued computer scientists for at least three decades. Genetic algorithms (GAs), invented by John Holland in the 1960s, are the most widely used approaches to computational evolution. In his book Adaptation in Natural and Arti cial Systems (Holland, 1975/1992, also reviewed in this issue), Holland presented GAs in a general theoretical framework for adaptation in nature.

abstract We describe the implementation and performance of a genetic algorithm which generates im... more abstract We describe the implementation and performance of a genetic algorithm which generates image feature extraction algorithms for remote sensing applications. We describe our basis set of primitive image operators and present our chromosomal representation of a complete algorithm. Our initial application has been geospatial feature extraction using publicly available multi-spectral aerial-photography data sets.

Analogy Making as a Complex Adaptive System Melanie Mitchell 1 INTRODUCTION This chapter describe... more Analogy Making as a Complex Adaptive System Melanie Mitchell 1 INTRODUCTION This chapter describes a computer program, called Copycat, that models how people make analogies. It might seem odd to include such a topic in a collection of chapters mostly on the immune system.

Identifying a shape's components can be essential for object recognition, object completion, and ... more Identifying a shape's components can be essential for object recognition, object completion, and shape matching, among other computer vision tasks [1]. In this paper we present a novel shape-decomposition algorithm, aimed at capturing some of the heuristics used by humans when parsing shapes. In 1984, Hoffman and Richards [2] proposed the minima rule, a simple heuristic for making straight-line cuts that decompose a given shape (or silhouette): Given a silhouette such as the one in Fig.

Science arises from the very human desire to understand and control the world. Over the course of... more Science arises from the very human desire to understand and control the world. Over the course of history, we humans have gradually built up a grand edifice of knowledge that enables us to predict, to varying extents, the weather, the motions of the planets, solar and lunar eclipses, the courses of diseases, the rise and fall of economic growth, the stages of language development in children, and a vast panorama of other natural, social, and cultural phenomena.

In our work we are studying how genetic algorithms (GAs) can evolve cellular automata (CAs) to pe... more In our work we are studying how genetic algorithms (GAs) can evolve cellular automata (CAs) to perform computations that require global coordination. The “evolving cellular automata” framework is an idealized means for studying how evolution (natural or computational) can create systems that perform emergent computation, in which the actions of simple components with local information and communication give rise to coordinated global information processing [3].

ABSTRACT A micro-world is described, in which many analogies involving strikingly different conce... more ABSTRACT A micro-world is described, in which many analogies involving strikingly different concepts and levels of subtlety can be made. The question" What differentiates the good ones from the bad ones?" is discussed, and then the problem of how to implement a computational model of the human ability to come up with such analogies (and to have a sense for their quality) is considered.

Abstract The building-block hypothesis states that the GA works well when short, low-order, highl... more Abstract The building-block hypothesis states that the GA works well when short, low-order, highly-fit schemas recombine to form even more highly fit higher-order schemas. The ability to produce fitter and fitter partial solutions by combining building blocks is believed to be a primary source of the GA's search power, but the GA research community currently lacks precise and quantitative descriptions of how schema processing actually takes place during the typical evolution of a GA search.

Abstract How can self-awareness emerge in a distributed system with no central control? How can s... more Abstract How can self-awareness emerge in a distributed system with no central control? How can such awareness feed back in a decentralized way to control the system's behavior? Many people have written about how selfawareness might come about in the brain. In this paper, I examine mechanisms for self-awareness and control in two other decentralized biological systems: the immune system and ant colonies. I then attempt to isolate some principles common to both systems.

In this article, the term biological computation refers to the proposal that living organisms the... more In this article, the term biological computation refers to the proposal that living organisms themselves perform computations, and, more specifically, that the abstract ideas of information and computation may be key to understanding biology in a more unified manner. It is important to point out that the study of biological computation is typically not the focus of the field of computational biology, which applies computing tools to the solution of specific biological problems.

What enables individually simple insects like ants to act with such precision and purpose as a gr... more What enables individually simple insects like ants to act with such precision and purpose as a group? How do trillions of individual neurons produce something as extraordinarily complex as consciousness? What is it that guides self-organizing structures like the immune system, the World Wide Web, the global economy, and the human genome? These are just a few of the fascinating and elusive questions that the science of complexity seeks to answer.

Abstract We present results from experiments in which a genetic algorithm (GA) was used to evolve... more Abstract We present results from experiments in which a genetic algorithm (GA) was used to evolve cellular automata (CAs) to perform a particular computational task-one-dimensional density classification. We look in detail at the evolutionary mechanisms producing the GA's behavior on this task and the impediments faced by the GA.

Abstract A simple evolutionary process can discover sophisticated methods for emergent informatio... more Abstract A simple evolutionary process can discover sophisticated methods for emergent information processing in decentralized spatially extended systems. The mechanisms underlying the resulting emergent computation are explicated by a technique for analyzing particle-based logic embedded in pattern-forming systems.

Abstract Genetic algorithms (GAs) play a major role in many artificial-life systems, but there is... more Abstract Genetic algorithms (GAs) play a major role in many artificial-life systems, but there is often little detailed understanding of why the GA performs as it does, and little theoretical basis on which to characterize the types of fitness landscapes that lead to successful GA performance. In this paper we propose a strategy for addressing these issues.

We present results from experiments in which a genetic algorithm (GA) is used to evolve 2D cellul... more We present results from experiments in which a genetic algorithm (GA) is used to evolve 2D cellular automata (CA) to perform a particular computational task (“density classification”) that requires globally coordinated information processing. The results are similar to that of earlier work on evolving 1D CAs. The behavior of the evolved 2D CAs is analyzed, and their performance is compared with that of several hand-designed 2D CAs.