2013 13th UK Workshop on Computational Intelligence (UKCI)最新文献_第5页

Transfer learning across heterogeneous tasks using behavioural genetic principles 使用行为遗传原理跨异构任务的迁移学习

2013 13th UK Workshop on Computational Intelligence (UKCI) Pub Date : 2013-09-01 DOI: 10.1109/UKCI.2013.6651300

Maitrei Kohli, G. D. Magoulas, M. Thomas

{"title":"Transfer learning across heterogeneous tasks using behavioural genetic principles","authors":"Maitrei Kohli, G. D. Magoulas, M. Thomas","doi":"10.1109/UKCI.2013.6651300","DOIUrl":"https://doi.org/10.1109/UKCI.2013.6651300","url":null,"abstract":"We explore the use of Artificial Neural Networks (ANNs) as computational models capable of sharing, retaining and reusing knowledge when they are combined via Behavioural Genetic principles. In behavioural genetics, the performance and the variability in performance (in case of population studies) stems from structure (intrinsic factors or genes) and environment (training dataset). We simulate the effects of genetic influences via variations in the neuro-computational parameters of the ANNs, and the effects of environmental influences via a filter applied to the training set. Our approach uses the twin method to disentangle genetic and environmental influences on performance, capturing transfer effects via changes to the heritability measure. Our model captures the wide range of variability exhibited by population members as they are trained on five different tasks. Preliminary experiments produced encouraging results as to the utility of this method. Results provide a foundation for future work in using a computational framework to capture population-level variability, optimising performance on multiple tasks, and establishing a relationship between selective pressure on cognitive skills and the change in the heritability of these skills across generations.","PeriodicalId":106191,"journal":{"name":"2013 13th UK Workshop on Computational Intelligence (UKCI)","volume":"68 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125575311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

A hybrid particle swarm optimization algorithm for parallel batch processing machines scheduling 并行批处理机器调度的混合粒子群优化算法

2013 13th UK Workshop on Computational Intelligence (UKCI) Pub Date : 2013-09-01 DOI: 10.1109/UKCI.2013.6651313

Jun-lin Chang, Ying Chen, Xiaoping Ma

引用次数: 5

Memetic algorithms for Cross-domain Heuristic Search 跨域启发式搜索的模因算法

2013 13th UK Workshop on Computational Intelligence (UKCI) Pub Date : 2013-09-01 DOI: 10.1109/UKCI.2013.6651303

E. Özcan, Shahriar Asta, Cevriye Altintas

{"title":"Memetic algorithms for Cross-domain Heuristic Search","authors":"E. Özcan, Shahriar Asta, Cevriye Altintas","doi":"10.1109/UKCI.2013.6651303","DOIUrl":"https://doi.org/10.1109/UKCI.2013.6651303","url":null,"abstract":"Hyper-heuristic Flexible Framework (HyFlex) is an interface designed to enable the development, testing and comparison of iterative general-purpose heuristic search algorithms, particularly selection hyper-heuristics. A selection hyper-heuristic is a high level methodology that coordinates the interaction of a fixed set of low level heuristics (operators) during the search process. The Java implementation of HyFlex along with different problem domains was recently used in a competition, referred to as Cross-domain Heuristic Search Challenge (CHeSC2011). CHeSC2011 sought for the best selection hyper-heuristic with the best median performance over a set of instances from six different problem domains. Each problem domain implementation contained four different types of operators, namely mutation, ruin-recreate, hill climbing and crossover. CHeSC2011 including the competing hyper-heuristic methods currently serves as a benchmark for hyper-heuristic research. Considering the type of the operators implemented under the HyFlex framework, CHeSC2011 could also be used as a benchmark to empirically compare the performance of appropriate variants of the evolutionary computation methods across a variety of problem domains for discrete optimisation. In this study, we investigate the performance and generality level of generic steady-state and transgenerational memetic algorithms which hybridize genetic algorithms with hill climbing across six problem domains of the CHeSC2011 benchmark.","PeriodicalId":106191,"journal":{"name":"2013 13th UK Workshop on Computational Intelligence (UKCI)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114437750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Evolving gene regulatory networks with mobile DNA mechanisms 进化基因调控网络与移动DNA机制

2013 13th UK Workshop on Computational Intelligence (UKCI) Pub Date : 2013-06-24 DOI: 10.1109/UKCI.2013.6651280

L. Bull, A. Adamatzky

引用次数: 3

Measuring the directional distance between fuzzy sets 测量模糊集之间的方向距离

2013 13th UK Workshop on Computational Intelligence (UKCI) Pub Date : 2013-01-01 DOI: 10.2139/ssrn.2828347

J. McCulloch, Christian Wagner, U. Aickelin

引用次数: 16

Towards the evolution of novel vertical-axis wind turbines 新型垂直轴风力涡轮机的发展

2013 13th UK Workshop on Computational Intelligence (UKCI) Pub Date : 2012-12-20 DOI: 10.1109/UKCI.2013.6651290

R. Preen, L. Bull

引用次数: 25