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.).

Machine learning

List of Figures. List of Tables. Preface. Foreword. 1. Basic Concepts. 2. Evolutionary Algorithm MOP Approaches. 3. MOEA Test Suites. 4. MOEA Testing and Analysis. 5. MOEA Theory and Issues. 3. MOEA Theoretical Issues. 6. Applications. 7. MOEA Parallelization. 8. Multi-Criteria Decision Making. 9. Special Topics. 10. Epilog. Appendix A: MOEA Classification and Technique Analysis. Appendix B: MOPs in the Literature. Appendix C: Ptrue & PFtrue for Selected Numeric MOPs. Appendix D: Ptrue & PFtrue for Side-Constrained MOPs. Appendix E: MOEA Software Availability. Appendix F: MOEA-Related Information. Index. References.

/pdf/evolutionary-algorithms-for-solving-multi-objective-problems-2txxk4mqci.pdf

Evolutionary algorithms for solving multi-objective problems

The field of metaheuristics for the application to combinatorial optimization problems is a rapidly growing field of research. This is due to the importance of combinatorial optimization problems for the scientific as well as the industrial world. We give a survey of the nowadays most important metaheuristics from a conceptual point of view. We outline the different components and concepts that are used in the different metaheuristics in order to analyze their similarities and differences. Two very important concepts in metaheuristics are intensification and diversification. These are the two forces that largely determine the behavior of a metaheuristic. They are in some way contrary but also complementary to each other. We introduce a framework, that we call the I&D frame, in order to put different intensification and diversification components into relation with each other. Outlining the advantages and disadvantages of different metaheuristic approaches we conclude by pointing out the importance of hybridization of metaheuristics as well as the integration of metaheuristics and other methods for optimization.

/pdf/metaheuristics-in-combinatorial-optimization-overview-and-menr0q3bxw.pdf

Metaheuristics in combinatorial optimization: Overview and conceptual comparison

The organization of behavior: A neuropsychological theory

I. the origin of species by means of natural selection

Epistasis for fitness means that the selective effect of a mutation is conditional on the genetic background in which it appears. Although epistasis is widely observed in nature, our understanding of its consequences for evolution by natural selection remains incomplete. In particular, much attention focuses only on its influence on the instantaneous rate of changes in frequency of selected alleles via epistatic contribution to the additive genetic variance for fitness. Thus, in this framework epistasis only has evolutionary importance if the interacting loci are simultaneously segregating in the population. However, the selective accessibility of mutational trajectories to high fitness genotypes may depend on the genetic background in which novel mutations appear, and this effect is independent of population polymorphism at other loci. Here we explore this second influence of epistasis on evolution by natural selection. We show that it is the consequence of a particular form of epistasis, which we designate sign epistasis. Sign epistasis means that the sign of the fitness effect of a mutation is under epistatic control; thus, such a mutation is beneficial on some genetic backgrounds and deleterious on others. Recent experimental innovations in microbial systems now permit assessment of the fitness effects of individual mutations on multiple genetic backgrounds. We review this literature and identify many examples of sign epistasis, and we suggest that the implications of these results may generalize to other organisms. These theoretical and empirical considerations imply that strong genetic constraint on the selective accessibility of trajectories to high fitness genotypes may exist and suggest specific areas of investigation for future research.

https://onlinelibrary.wiley.com/doi/pdf/10.1111/j.0014-3820.2005.tb01768.x

Perspective:sign epistasis and genetic constraint on evolutionary trajectories

/pdf/sign-epistasis-and-genetic-constraint-on-evolutionary-1blunvk5oe.pdf

Sign epistasis and genetic constraint on evolutionary trajectories

One common characterization of how simple hill-climbing optimization methods can fail is that they become trapped in local optima - a state where no small modification of the current best solution will produce a solution that is better. This measure of 'better' depends on the performance of the solution with respect to the single objective being optimized. In contrast, multi-objective optimization (MOO) involves the simultaneous optimization of a number of objectives. Accordingly, the multi-objective notion of 'better' permits consideration of solutions that may be superior in one objective but not in another. Intuitively, we may say that this gives a hill-climber in multi-objective space more freedom to explore and less likelihood of becoming trapped. In this paper, we investigate this intuition by comparing the performance of simple hill-climber-style algorithms on single-objective problems and multi-objective versions of those same problems. Using an abstract building-block problem we illustrate how 'multi-objectivizing' a single-objective optimization (SOO) problem can remove local optima. Then we investigate small instances of the travelling salesman problem where additional objectives are defined using arbitrary sub-tours. Results indicate that multi-objectivization can reduce local optima and facilitate improved optimization in some cases. These results enlighten our intuitions about the nature of search in multi-objective optimization and sources of difficulty in single-objective optimization.

Reducing Local Optima in Single-Objective Problems by Multi-objectivization

Embodied Evolution: Distributing an evolutionary algorithm in a population of robots

Two important problems in genetic programming (GP) are its tendency to find unnecessarily large trees (bloat), and the general evolutionary algorithms problem that diversity in the population can be lost prematurely. The prevention of these problems is frequently an implicit goal of basic GP. We explore the potential of techniques from multi-objective optimization to aid GP by adding explicit objectives to avoid bloat and promote diversity. The even 3, 4, and 5-parity problems were solved efficiently compared to basic GP results from the literature. Even though only non-dominated individuals were selected and populations thus remained extremely small, appropriate diversity was maintained. The size of individuals visited during search consistently remained small, and solutions of what we believe to be the minimum size were found for the 3, 4, and 5-parity problems.

Richard A. Watson

Papers

Perspective:sign epistasis and genetic constraint on evolutionary trajectories

Sign epistasis and genetic constraint on evolutionary trajectories

Reducing Local Optima in Single-Objective Problems by Multi-objectivization

Embodied Evolution: Distributing an evolutionary algorithm in a population of robots

Reducing bloat and promoting diversity using multi-objective methods