Introduction

Rawlins, Gregory J. E.

doi:10.1016/b978-0-08-050684-5.50003-3

Cited by 25 publications

(25 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Genetic algorithm is a search and optimization method which is based on natural selection [7,[11][12]. Genetic algorithms randomly generate multiple solutions.…”

Section: Genetic Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Performance Evaluations for OpenMP Accelerated Training Of Separable Image Filter

Uzun¹,

Akgün²

2016

International Journal of Applied Mathematics, Electronics and Computers

View full text Add to dashboard Cite

Abstract:One of the widespread image processing applications is image filtering with two dimensional convolution. Determining the weights of image filters are of importance for the success of filtering operation. Heuristic algorithms such as genetic algorithms provide an efficient way of training these types of filters. Due to the high computational cost of repetitive image filtering operations, this process may take hours to implement using single core computing. OpenMP (Open Multi Processing) provides an efficient library for utilizing the computing power of multicore processors. In this study, OpenMP accelerated training of separable filters that are a subclass of convolution filters has been implemented based on genetic algorithms. Comparative speed-up results for various sizes of images using various sizes of filtering kernels were presented. Also the effect of population size of genetic algorithm and the number of working cores have been investigated.

show abstract

“…Genetic algorithm is a search and optimization method which is based on natural selection [7,[11][12]. Genetic algorithms randomly generate multiple solutions.…”

Section: Genetic Algorithmsmentioning

confidence: 99%

“…Weights can readily be obtained using different analytical techniques [2][3]. In another approach, the kernel weights can be trained using the original and noisy image samples [4][5][6][7]. Heuristic algorithms provide an efficient way for the computation of the filter kernel weights [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluations for OpenMP Accelerated Training Of Separable Image Filter

Uzun¹,

Akgün²

2016

International Journal of Applied Mathematics, Electronics and Computers

View full text Add to dashboard Cite

show abstract

“…The denominator H(f (S)) calculates the entropy over the marginal distribution of possible fitness values of f (S) and scales ξ i to a range of [0,1]. A gene significance value close to 0 implies that the gene contributes very little to the fitness.…”

Section: A Gene Significancementioning

confidence: 99%

“…With respect to evolutionary algorithms, epistasis refers to the influence of interacting genes on the overall fitness of the genotype [1]. As such, epistasis plays an important role on the search difficulty of a problem.…”

Section: Introductionmentioning

confidence: 99%

Epistasis in Multi-Objective Evolutionary Recurrent Neuro-Controllers

Ventresca

Ombuki-Berman

2007

2007 IEEE Symposium on Artificial Life

View full text Add to dashboard Cite

Abstract-This paper presents an information-theoretic analysis of the epistatic effects present in evolving recurrent neural networks. That is, how do the gene-gene interactions change as the evolutionary process progresses and what does this reveal about the problem difficulty. Also, to what end does the environment influence epistasis. Our investigation concentrates on multi-objective evolution, where the major task to be performed is broken into sub-tasks which are then used as our objectives. Our results show that the behavior of epistasis during the evolutionary process is strongly dependant on the environment. The experimental results are presented for the path finding robot application using continuous-time and spiking neuro-controllers.

show abstract

“…Much work has been done on the foundations of GAs (see, for example, [7,17,23,24,251). The traditional theory of GAs (first formulated by Holland [25]) assumes that, at avery general level of description, GAS work by discovering, etnphasizing, and recombining good building blocks of solutions in a highly parallel fashion.…”

Section: How Anal Why Do Genetic Algorithms Work?mentioning

confidence: 99%

Genetic algorithms: An overview

Mitchell

1995

Complexity

185

View full text Add to dashboard Cite

verwiewhe goals of creating artificial intelligence and artificial life stem from the very beginnings of the computer age. The earliest computer scientists-Alan Turing, JohnVon Neuniann, Norbert Weiner, and others-were motivated in large part by visions of imbuing computer programs with intelligence, with the life-like ability to self-replicate, and with the adaptive capability to learn and to control their environments. These early pioneers of computer science were as much interested in biology and psychology as in electronics, and looked to natural systems as guiding metaphors for lion7 to achieve their visions. It should be no surprise, then, that from the earliest days, computers were applied not only to calculating missile trajectories and deciphering military codes, but also to modeling the brain, mimicking human learning, and simulating biological evolution. These biologically motivated computing activities have waxed and waned over the last 40 years, but in the last ten years they have all undergone a resurgence in the computation research community. The first has grown into the field of neural networks, the second into machine learning, and the third into what is now called "evolutionary computation," of which genetic algorithms (GAS) are the most prominent example.GAS were first described by John Holland in the 1960s and further developed by Holland and his students and colleagues at the University of Michigan in the 1960s and 1970s. Holland's goal was to understand the phenomenon of "adaptation" as it occurs in nature and to develop ways in which the mechanisms of natural adaptation might be imported into computer systems. Holland's 1975 book Adaptation in Natural andilrtificial Sysrerns [25] presented the GA as an abstraction of biological evolution and gave a theoretical framework for adaptation under the GA. Holland's GA is a method for moving from one population of "chromosomes" (e.g., strings of "bits" representing candidate solutions to a problem) to a new population, using "selection" together with the genetics-inspired operators of crossover, mutation, and inversion. Each chromosome consists of "genes" ( e g , bits), with each gene being an instance of a particular "allele" (e.g., 0 or 1). The selection operator chooses those chromosomes in the population that will be allowed to reproduce, with fitter chromosomes producing on average more offspring t h a n less fit ones. Crossover exchanges subparts of two chromosomes, r o LI gh 1 y mi mi c ki n g biological recombinati o n bet ween two single -ch r o mo s o m e ("haploid") organisms; mutation randomly changes the allele values of some locations in the chromosome; and inversion reverses the order of a contiguous section of the chromosome, thus rearranging the order in which genes are arrayed. THE APPEAL 08: EWOLUFIQMWhy use evolution as an inspiration for solving computational problems? The mechanisms of evolution seem well-suited for some of the most pressing computational problems in many fields. Many computational problems involve searchin...

show abstract

Introduction

Cited by 25 publications

References 0 publications

Performance Evaluations for OpenMP Accelerated Training Of Separable Image Filter

Performance Evaluations for OpenMP Accelerated Training Of Separable Image Filter

Epistasis in Multi-Objective Evolutionary Recurrent Neuro-Controllers

Genetic algorithms: An overview

Contact Info

Product

Resources

About