Melanie Mitchell

Melanie Mitchell
Portland State University | PSU · Department of Computer Science

About

64
Publications
16,301
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
16,363
Citations

Publications

Publications (64)
Article
Medical image segmentation is typically performed manually by a physician to delineate gross tumor volumes for treatment planning and diagnosis. Manual segmentation is performed by medical experts using prior knowledge of organ shapes and locations but is prone to reader subjectivity and inconsistency. Automating the process is challenging due to p...
Conference Paper
We investigate the role of learned shape-prototypes in an influential family of hierarchical neural-network models of vision. Central to these networks' design is a dictionary of learned shapes, which are meant to respond to discriminative visual patterns in the input. While higher-level features based on such learned prototypes have been cited as...
Conference Paper
Hierarchical networks are known to achieve high classification accuracy on difficult machine-learning tasks. For many applications, a clear explanation of why the data was classified a certain way is just as important as the classification itself. However, the complexity of hierarchical networks makes them ill-suited for existing explanation method...
Article
Full-text available
Many approaches to machine learning require a system to learn a model from a set of training examples that the model must classify, or training problems that the model must solve. How are these training cases to be chosen? Typically, due to the costs of acqui-sition or computation, only a relatively small sample from the universe of possible proble...
Article
Full-text available
We explore the role of spatial distribution of populations in coevolutionary learning by comparing the performance of several different evolutionary methods on two different tasks. Our experiments show that spatial coevolution is substantially more successful than any of the other methods we tried. One reason for this, demonstrated by our results,...
Article
Full-text available
A novel genetic algorithm (GA) is presented here that performs level set curve evolution using texture and shape information to automatically segment the prostate on pelvic images in computed tomography and magnetic resonance imaging modalities. Here, the segmenting contour is represented as a level set function. The contours in a typical level set...
Conference Paper
This paper presents a genetic algorithm (GA) for combining representations of learned priors such as shape, regional properties and relative location of organs into a single framework in order to perform automated segmentation of the prostate. Prostate segmentation is typically performed manually by an expert physician and is used to determine the...
Article
Full-text available
A novel technique is presented to combine genetic algorithms (GAs) with level-set functions to segment objects with known shapes and variabilities on images. The individuals of the GA, also known as chromosomes consist of a sequence of parameters of a level-set function. Each chromosome represents a unique segmenting contour. An initial population...
Conference Paper
Full-text available
This paper presents a new technique for segmenting thermographic images using a genetic algorithm (GA). The individuals of the GA also known as chromosomes consist of a sequence of parameters of a level set function. Each chromosome represents a unique segmenting contour. An initial population of segmenting contours is generated based on the learne...
Conference Paper
Full-text available
The notion of conceptual structure in CA rules that perform the density classification task (DCT) was introduced by [1]. Here we investigate the role of process-symmetry in CAs that solve the DCT, in particular the idea of conceptual similarity, which defines a novel search space for CA rules. We report on two new process-symmetric one-dimensional...
Conference Paper
Full-text available
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 shap...
Conference Paper
Full-text available
We formulate decomposition of two-dimensional shapes as a combinatorial optimization problem and present a dynamic programming algorithm that solves it.
Article
In this article, I discuss some recent ideas in complex systems on the topic of networks, contained in or inspired by three recent complex systems books. The general science of networks is the subject of Albert-Lazlo Barabasi's Linked [A.-L. Barabasi, Linked: The New Science of Networks, Perseus, New York, 2002] and Duncan Watts' Six Degrees [D. Wa...
Conference Paper
Full-text available
Segmentation of medical images is challenging due to poor image contrast and artifacts that result in missing or diffuse organ/tissue boundaries. Consequently, this task involves incorporating as much prior information as possible (e.g., texture, shape, and spatial location of organs) into a single framework. In this paper, we present a genetic alg...
Conference Paper
Full-text available
We investigate the results of coevolution of spatially distributed populations. In particular, we describe work in which a simple function approximation problem is used to compare different spatial evolutionary methods. Our work shows that, on this problem, spatial coevolution is dramatically more successful than any other spatial evolutionary sche...
Conference Paper
Full-text available
How can self-awareness emerge in a distributed sys- tem 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 self- awareness might come about in the brain. In this paper, I examine mechanisms for self-awareness and control in two other decentralized bio...
Conference Paper
Here we present preliminary results in which a genetic algorithm (GA) is used to evolve one-dimensional binary-state cellular automata (CA) to perform a non-trivial task requiring collective behavior. Using a fitness function that is an average area in the iterative map, the GA discovers rules that produce a period-3 oscillation in the concentratio...
Article
Full-text available
We present a comparative study of an evolutionary and a coevolutionary search model. In the latter, strategies for solving a problem coevolve with training cases. We find that the coevolutionary model has a relatively large efficacy: 41 out of 50 (82%) of the simulations produce high quality strategies. In contrast, the evolutionary model has a ver...
Article
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 a...
Article
Full-text available
This paper argues for the possibility of 'artificial life' and computational evolution, first by discussing (via a highly simplified version) John von Neumann's self-reproducing automation and then by presenting some recent work focusing on computational evolution, in which 'cellular automata', a form of parallel and decentralized computing system,...
Article
Full-text available
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 d...
Article
Full-text available
This paper reports the application of new methods for detecting computation in nonlinear processes to a simple evolutionary model that allows us to directly address these questions. The main result is the evolutionary discovery of methods for emergent global computation in a spatially distributed system consisting of locally interacting processors....
Article
Full-text available
this paper we focus on how these CAs implement the emergent computational strategies for performing a task. In particular, we develop a class of embedded-particle models to describe the computational strategies implemented by particular CAs. To do this, we use the computational mechanics framework of Crutchfield and Hanson [2, 6], in which a CA's i...
Article
Full-text available
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...
Article
. 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 mutation-only genetic algorithm (GA) is introduced that identifies a new and general mechanism causing meta...
Article
Full-text available
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...
Article
Full-text available
. We introduce a class of embedded-particle models for describing the emergent computational strategies observed in cellular automata (CAs) that were evolved for performing certain computational tasks. The models are evaluated by comparing their estimated performances with the actual performances of the CAs they model. The results show, via a close...
Article
Full-text available
This paper 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 papers mostly on the immune system. However, the immune system is one of many systems in nature in which a very large collection of relatively simple agents, operating with no central control a...
Article
Full-text available
Evolving one-dimensional cellular automata (CAs) with genetic algorithms has provided insight into how improved performance on a task requiring global coordination emerges when only local interactions are possible. Two approaches that can affect the search efficiency of the genetic algorithm are coevolution, in which a population of problems -- in...
Article
Full-text available
We investigate the ability of a genetic algorithm to design cellular automata that perform computations. The computational strategies of the resulting cellular automata can be understood using a framework in which ``particles'' embedded in space-time configurations carry information and interactions between particles effect information processing....
Article
. 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 simple genetic algorithm (GA) is developed that identifies a general mechanism that causes metastability i...
Article
Introduction Cellular automata (CAs) are decentralized spatially extended systems consisting of large numbers of simple identical components with local connectivity. Such systems have the potential to perform complex computations with a high degree of efficiency and robustness, as well as to model the behavior of complex systems in nature. For thes...
Article
We introduce an analytical model that predicts the dynamics of a simple evolutionary algorithm in terms of the flow in the space of fitness distributions. In the limit of infinite populations the dynamics is derived in closed form. We show how finite populations induce periods of stasis - ???fitness epochs??? - and rapid jumps - ???innovations???....
Article
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. Understanding how globally coordinated co...
Article
Genetic algorithms (GAs) are computer programs that mimic the processes of biological evolution in order to solve problems and to model evolutionary systems. In this paper I describe the appeal of using ideas from evolution to solve computational problems, give the elements of simple GAs, survey some application areas of GAs, and give a detailed ex...
Article
ial costs incurred in having centralized coordination, not the least being (i) speed (a central coordinator can be a bottleneck to fast information processing); (ii) robustness (if the central coordinator is injured or lost, the entire system collapses) ; and (iii) equitable resource allocation (a central controller must be allocated a lion's share...
Article
Genetic algorithms are computational models of evolution that play a central role in many artificial-life models. We review the history and current scope of research on genetic algorithms in artificial life, using illustrative examples in which the genetic algorithm is used to study how learning and evolution interact, and to model ecosystems, immu...
Article
Full-text available
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....
Article
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 currentl...
Article
Full-text available
What makes a problem easy or hard for a genetic algorithm (GA)? This question has become increasingly important as people have tried to apply the GA to ever more diverse types of problems. Much previous work on this question has studied the relationship between GA performance and the structure of a given fitness function when it is expressed as a W...
Article
Full-text available
We present results from an experiment similar to one performed by Packard [24], in which a genetic algorithm is used to evolve cellular automata (CA) to perform a particular computational task. Packard examined the frequency of evolved CA rules as a function of Langton's parameter [17], and interpreted the results of his experiment as giving eviden...
Conference Paper
Full-text available
How does evolution produce sophisticated emergent computation in systems composed of simple components limited to local interactions? To model such a process, we used a genetic algorithm (GA) to evolve cellular automata to perform a computational task requiring globally-coordinated information processing. On most runs a class of relatively unsophis...
Article
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. In particular, we identif...
Article
Full-text available
We analyze a simple hill-climbing algorithm (RMHC) that was previously shown to outperform a genetic algorithm (GA) on a simple "Royal Road" function. We then analyze an "idealized" genetic algorithm (IGA) that is significantly faster than RMHC and that gives a lower bound for GA speed. We identify the features of the IGA that give rise to this spe...
Article
Full-text available
In this paper we review previous work and present new work concerning the relationship between dynamical systems theory and computation. In particular, we review work by Langton \cite{Langton90} and Packard \cite{Packard88} on the relationship between dynamical behavior and computational capability in cellular automata (CA). We present results from...
Article
Full-text available
In this paper we review some previously published experimental results in which a simple hill-climbing algorithm---Random Mutation Hill-Climbing (RMHC)---significantly outperforms a genetic algorithm on a simple ``Royal Road'' function. We present an analysis of RMHC followed by an analysis of an ``idealized'' genetic algorithm (IGA) that is in tur...
Conference Paper
Full-text available
In this paper we discuss a number of seemingly anomalous results reported by Tanese concerning the performance of the genetic algorithm (GA) on a subclass of Walsh polynomials. Tanese found that the GA optimized these functions poorly and that a partitioning of a single large population into a number of smaller independent populations seemed to imp...
Article
This paper describes Copycat, a computer model of the mental mechanisms underlying the fluidity and adaptability of the human conceptual system in the context of analogy-making. Copycat creates analogies between idealized situations in a microworld that has been designed to capture and isolate many of the central issues of analogy-making. In Copyca...
Article
A novel genetic algorithm (GA) is presented here that performs level-set curve evolution using texture and shape information to automatically segment the prostate on pelvic images in computed tomography and magnetic resonance imaging modalities. Here, the segmenting contour is represented as a level-set function. The contours in a typical level- se...
Article
The overall goals of the project are to determine the usefulness of genetic algorithms (GAs) in designing spatially extended parallel systems to perform computational tasks and to develop theoretical frameworks both for understanding the computation in the systems evolved by the GA and for understanding the evolutionary process which successful sys...