Genetic Algorithms

https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

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

From the Publisher:

"This is the best general book on Genetic Algorithms written to date. It covers background, history, and motivation; it selects important, informative examples of applications and discusses the use of Genetic Algorithms in scientific models; and it gives a good account of the status of the theory of Genetic Algorithms. Best of all the book presents its material in clear, straightforward, felicitous prose, accessible to anyone with a college-level scientific background. If you want a broad, solid understanding of Genetic Algorithms -- where they came from, what's being done with them, and where they are going -- this is the book.
-- John H. Holland, Professor, Computer Science and Engineering, and Professor of Psychology, The University of Michigan; External Professor, the Santa Fe Institute. 
Genetic algorithms have been used in science and engineering as adaptive algorithms for solving practical problems and as computational models of natural evolutionary systems. This brief, accessible introduction describes some of the most interesting research in the field and also enables readers to implement and experiment with genetic algorithms on their own. It focuses in depth on a small set of important and interesting topics -- particularly in machine learning, scientific modeling, and artificial life -- and reviews a broad span of research, including the work of Mitchell and her colleagues. 
The descriptions of applications and modeling projects stretch beyond the strict boundaries of computer science to include dynamical systems theory, game theory, molecular biology, ecology, evolutionary biology, and population genetics, underscoring the exciting "general purpose" nature of genetic algorithms as search methods that can be employed across disciplines. 
An Introduction to Genetic Algorithms is accessible to students and researchers in any scientific discipline. It includes many thought and computer exercises that build on and reinforce the reader's understanding of the text. 
The first chapter introduces genetic algorithms and their terminology and describes two provocative applications in detail. The second and third chapters look at the use of genetic algorithms in machine learning (computer programs, data analysis and prediction, neural networks) and in scientific models (interactions among learning, evolution, and culture; sexual selection; ecosystems; evolutionary activity). Several approaches to the theory of genetic algorithms are discussed in depth in the fourth chapter. The fifth chapter takes up implementation, and the last chapter poses some currently unanswered questions and surveys prospects for the future of evolutionary computation.

/pdf/an-introduction-to-genetic-algorithms-32faq13a56.pdf

An Introduction to Genetic Algorithms

Data Mining Practical Machine Learning Tools and Techniques

Specifically, we apply genetic algorithms that include diploid genotypes and dominance operators to a simple nonstationary problem in function optimization: an oscillating, blind knapsack problem. In doing this, we find that diploidy and dominance induce a form of long term distributed memory that stores and occasionally remembers good partial solutions that were once desirable. This memory permits faster adaptation to drastic environmental shifts than is possible without the added structures and operators. This paper investigates the use of diploid representations and dominance operators in genetic algorithms (GAs) to improve performance in environments that vary with time. The mechanics of diploidy and dominance in natural genetics are briefly discussed, and the usage of these structures and operators in other GA investigations is reviewed. An extension of the schema theorem is developed which illustrates the ability of diploid GAs with dominance to hold alternative alleles in abeyance. Both haploid and diploid GAs are applied to a simple time varying problem: an oscillating, blind knapsack problem. Simulation results show that a diploid GA with an evolving dominance map adapts more quickly to the sudden changes in this problem environment than either a haploid GA or a diploid GA with a fixed dominance map. These proof-of-principle results indicate that diploidy and dominance can be used to induce a form of long term distributed memory within a population of structures. In the remainder of this paper, we explore the mechanism, theory, and implementation of dominance and diploidy in artificial genetic search. We start by examining the role of diploidy and dominance in natural genetics, and we briefly review examples of their usage in genetic algorithm circles. We extend the schema theorem to analyze the effect of these structures and mechanisms. We present results from computational experiments on a 17-object, oscillating, blind 0-1 knapsack problem. Simulations with adaptive dominance maps and diploidy are able to adapt more quickly to sudden environmental shifts than either a haploid genetic algorithm or a diploid genetic algorithm with fixed dominance map. These results are encouraging and suggest the investigation of dominance and diploidy in other GA applications in search and machine learning. INTRODUCTION Real world problems are seldom independent of time. If you don't like the weather, wait five minutes and it will change. If this week gasoline costs $1.30 a gallon, next week it may cost $0.89 a gallon or perhaps $2.53 a gallon. In these and many more complex ways, real world environments are both nonstationary and noisy. Searching for good solutions or good behavior under such conditions is a difficult task; yet, despite the perpetual change and uncertainty, all is not lost. History does repeat itself, and what goes around does come around. The horrors of Malthusian extrapolation rarely come to pass, and solutions that worked well yesterday are at least somewhat likely to be useful when circumstances are somewhat similar tomorrow or the day after. The temporal regularity implied in these observations places a premium on search augmented by selective memory. In other words, a system which does not learn the lessons of its history is doomed to repeat its mistakes. THE MECHANICS OF NATURAL DOMINANCE AND DIPLOIDY It is surprising to some genetic algorithm newcomers that tpe most commonly used GA is modeled after the mechanics of haploid genetics. After all, don't most elementary genetics textbooks start off with a discussion of Mendel's pea plants and some mention of diploidy and dominance? The reason for this disparity between genetic algorithm practice and genetics textbook coverage is due to the success achieved by early GA investigators (Hollstien, 1971; De Jong, 1975) using haploid chromosome models on stationary problems. It was found that surprising efficacy and efficiency could be obtained using single stranded (haploid) chromosomes under the action of reproduction and crossover. As a result, later investigators of artificial genetic search have tended to ignore diploidy and dominance. In this section we examine the mechanics of diploidy and dominance to understand their roles in shielding alternate In this paper, we investigate the behavior of a genetic algorithm augmented by structures and operators capable of exploiting the regularity and repeatability of many nonstationary environments.

Nonstationary function optimization using genetic algorithm with dominance and diploidy

This paper describes an immune system model based on binary strings. The purpose of the model is to study the pattern-recognition processes and learning that take place at both the individual and species levels in the immune system. The genetic algorithm (GA) is a central component of the model. The paper reports simulation experiments on two pattern-recognition problems that are relevant to natural immune systems. Finally, it reviews the relation between the model and explicit fitness-sharing techniques for genetic algorithms, showing that the immune system model implements a form of implicit fitness sharing.

https://cs.unm.edu/~forrest/publications/immune-92.pdf

Using genetic algorithms to explore pattern recognition in the immune system

In typical applications, genetic algorithms (GAs) process populations of potential problem solutions to evolve a single population member that specifies an 'optimized' solution. The majority of GA analysis has focused on these optimization applications. In other applications (notably learning classifier systems and certain connectionist learning systems), a GA searches for a population of cooperative structures that jointly perform a computational task. This paper presents an analysis of this type of GA problem. The analysis considers a simplified genetics-based machine learning system: a model of an immune system. In this model, a GA must discover a set of pattern-matching antibodies that effectively match a set of antigen patterns. Analysis shows how a GA can automatically evolve and sustain a diverse, cooperative population. The cooperation emerges as a natural part of the antigen-antibody matching procedure. This emergent effect is shown to be similar to fitness sharing, an explicit technique for multimodal GA optimization. Further analysis shows how the GA population can adapt to express various degrees of generalization. The results show how GAs can automatically and simultaneously discover effective groups of cooperative computational structures.

https://cs.unm.edu/~forrest/publications/immune-93a.pdf

Searching for diverse, cooperative populations with genetic algorithms

GAS have proven effective on a broad range of search problems. However, when each population member’s fitness evaluation is computationally expensive, the prospect of evaluating an entire population can prohibit use of the GA. This paper examines a GA that overcomes this difficulty by evaluating only a portion of the population. The remainder of the population has its fitness assigned by inheritance. Theoretical arguments justify this approach. An application to a GA-easy problem shows that greater efficiency can be obtained by evaluating only a small portion of the population. A real-world search problem confirms these results. Implications and future directions are discussed.

Fitness inheritance in genetic algorithms

We asked "What is a Learning Classifier System" to some of the best-known researchers in the field. These are their answers.

Robert E. Smith

Papers

Nonstationary function optimization using genetic algorithm with dominance and diploidy

Using genetic algorithms to explore pattern recognition in the immune system

Searching for diverse, cooperative populations with genetic algorithms

Fitness inheritance in genetic algorithms

What Is a Learning Classifier System