Evolutionary Multitasking: A Computer Science View of Cognitive Multitasking

详细信息    查看全文

• 作者：Yew-Soon Ong ; Abhishek Gupta
• 关键词：Multitask optimization ; Evolutionary multitasking ; Evolutionary algorithm ; Cross ; domain optimization ; Memetic computation
• 刊名：Cognitive Computation
• 出版年：2016
• 出版时间：April 2016
• 年：2016
• 卷：8
• 期：2
• 页码：125-142
• 全文大小：3,433 KB
• 参考文献：1.Dzubak CM. Multitasking: the good, the bad, and the unknown. J Assoc Tutor Prof. 2008;1(2):1–12.
  2.Adler RF, Benbunan-Fich R. Juggling on a high wire: multitasking effects on performance. Int J Hum Comput Stud. 2012;70(2):156–68.CrossRef
  3.Salvucci DD, Taatgen NA. Threaded cognition: an integrated theory of concurrent multitasking. Psychol Rev. 2008;115(1):101.CrossRef PubMed
  4.Just MA, Buchweitz A. What brain imaging reveals about the nature of multitasking. In: Chipman S, editor. The Oxford handbook of cognitive science. New York: Oxford University Press; 2011. Available from www.​ccbi.​cmu.​edu/​reprints/​Just-Buchweitz_​Chipman_​handbook%20​chapt_​multitasking.​pdf .
  5.Caruana R. Multitask learning. Mach Learn. 1997;28(1):41–75.CrossRef
  6.Bäck T, Hammel U, Schwefel HP. Evolutionary computation: comments on the history and current state. IEEE Trans Evol Comput. 1997;1(1):3–17.CrossRef
  7.Golberg DE. Genetic algorithms in search, optimization, and machine learning. Boston: Addion wesley; 1989.
  8.Srinivas M, Patnaik LM. Genetic algorithms: a survey. Computer. 1994;27(6):17–26.CrossRef
  9.Grefenstette JJ, Baker JE. How genetic algorithms work: a critical look at implicit parallelism. In Proceedings of the third international conference on Genetic algorithms 1989 Dec 1. Morgan Kaufmann Publishers Inc. pp. 20–27.
  10.Bertoni A, Dorigo M. Implicit parallelism in genetic algorithms. Artif Intell. 1993;61(2):307–14.CrossRef
  11.Wright AH, Vose MD, Rowe JE. Implicit parallelism. In: Genetic and evolutionary computation—GECCO. Berlin, Heidelberg: Springer; 2003. pp. 1505–1517.
  12.Seada H, Deb K. A unified evolutionary optimization procedure for single, multiple, and many objectives. doi:10.​1109/​TEVC.​2015.​2459718 .
  13.Deb K, Pratap A, Agarwal S, Meyarivan T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Comput. 2002;6(2):182–97.CrossRef
  14.Deb K. Multi-objective optimization using evolutionary algorithms. London: Wiley; 2001.
  15.Ishibuchi H, Tsukamoto N, Nojima Y. Evolutionary many-objective optimization: a short review. In: IEEE congress on evolutionary computation; 2008 Jun 1. pp. 2419–2426.
  16.Asafuddoula M, Ray T, Sarker R. A decomposition based evolutionary algorithm for many objective optimization. IEEE Trans Evol Comput. 2014;19(3):445–60.CrossRef
  17.Gupta A, Ong YS, Feng L. Multifactorial evolution: toward evolutionary multitasking. Accepted IEEE Trans Evol Comput. doi:10.​1109/​TEVC.​2015.​2458037 .
  18.Rice JO, Cloninger CR, Reich TH. Multifactorial inheritance with cultural transmission and assortative mating. I. Description and basic properties of the unitary models. Am J Hum Genet. 1978;30(6):618.PubMed PubMedCentral
  19.Cloninger CR, Rice J, Reich T. Multifactorial inheritance with cultural transmission and assortative mating. II. A general model of combined polygenic and cultural inheritance. Am J Hum Genet. 1979;31(2):176.PubMed PubMedCentral
  20.Chen X, Ong YS, Lim MH, Tan KC. A multi-facet survey on memetic computation. IEEE Trans Evol Comput. 2011;15(5):591–607.CrossRef
  21.Ong YS, Lim MH, Chen X. Research frontier-memetic computation—past, present & future. IEEE Comput Intell Mag. 2010;5(2):24.CrossRef
  22.Dawkins R. The selfish gene. Oxford: Oxford University Press; 2006.
  23.Cavalli-Sforza LL, Feldman MW. Cultural versus biological inheritance: phenotypic transmission from parents to children. (A theory of the effect of parental phenotypes on children’s phenotypes). Am J Hum Genet. 1973;25(6):618.PubMed PubMedCentral
  24.Feldman MW, Laland KN. Gene-culture coevolutionary theory. Trends Ecol Evol. 1996;11(11):453–7.CrossRef PubMed
  25.Krawiec K, Wieloch B. Automatic generation and exploitation of related problems in genetic programming. In: IEEE congress on evolutionary computation (CEC); 2010 Jul 18, pp. 1–8.
  26.Bean JC. Genetic algorithms and random keys for sequencing and optimization. ORSA J Comput. 1994;6(2):154–60.CrossRef
  27.Gonçalves JF, Resende MG. Biased random-key genetic algorithms for combinatorial optimization. J Heuristics. 2011;17(5):487–525.CrossRef
  28.Chauhan P, Deep K, Pant M. Novel inertia weight strategies for particle swarm optimization. Memetic Comput. 2013;5(3):229–51.CrossRef
  29.Ong YS, Zhou Z, Lim D. Curse and blessing of uncertainty in evolutionary algorithm using approximation. In: Congress on evolutionary computation; 2006, pp. 2928–2935.
  30.Ong YS, Keane AJ. Meta-Lamarckian learning in memetic algorithms. IEEE Trans Evol Comput. 2004;8(2):99–110.CrossRef
  31.Deb K, Agrawal RB. Simulated binary crossover for continuous search space. Complex Syst. 1994;9(3):1–15.
  32.Watson RA, Jansen T. A building-block royal road where crossover is provably essential. In: Proceedings of the 9th annual conference on Genetic and evolutionary computation, ACM; 2007 Jul 7, pp. 1452–1459.
  33.Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng. 2010;22(10):1345–59.CrossRef
  34.Feng L, Ong YS, Lim M, Tsang I. Memetic search with inter-domain learning: a realization between CVRP and CARP. IEEE Trans Evol Comput. 2014;19(5):644–58.CrossRef
  35.Feng L, Ong YS, Tan AH, Tsang IW. Memes as building blocks: a case study on evolutionary optimization + transfer learning for routing problems. Memetic Comput. 2015;7(3):159–80.CrossRef
  36.Besada-Portas E, de la Torre L, de la Cruz JM, de Andrés-Toro B. Evolutionary trajectory planner for multiple UAVs in realistic scenarios. IEEE Trans Robot. 2010;26(4):619–34.CrossRef
  37.Deb K, Sindhya K, Okabe T. Self-adaptive simulated binary crossover for real-parameter optimization. In: Proceedings of the Genetic and evolutionary computation conference (GECCO-2007), UCL London; 2007, pp. 1187–1194.
  38.Poli R, Langdon WB. Schema theory for genetic programming with one-point crossover and point mutation. Evol Comput. 1998;6(3):231–52.CrossRef PubMed
  39.Ong YS, Nair PB, Keane AJ. Evolutionary optimization of computationally expensive problems via surrogate modeling. AIAA J. 2003;41(4):687–96.CrossRef
  40.Dantzig GB, Ramser JH. The truck dispatching problem. Manage Sci. 1959;6(1):80–91.CrossRef
  41.Solomon MM. Algorithms for the vehicle routing and scheduling problems with time window constraints. Oper Res. 1987;35(2):254–65.CrossRef
  42.Avigad G, Moshaiov A. Set-based concept selection in multi-objective problems: optimality versus variability approach. J Eng Des. 2009;20(3):217–42.CrossRef
  43.Avigad G, Moshaiov A, Brauner N. MOEA-based approach to delayed decisions for robust conceptual design. In: Applications of evolutionary computing. Berlin, Heidelberg: Springer; 2005 Jan 1, pp. 584–589.
  44.Avigad G, Moshaiov A. Interactive evolutionary multiobjective search and optimization of set-based concepts. IEEE Trans Syst Man Cybernet B Cybernet. 2009;39(4):1013–27.CrossRef
  45.Gupta A. Numerical modelling and optimization of non-isothermal, rigid tool liquid composite moulding processes (Doctoral dissertation, ResearchSpace@ Auckland). 2013.
  46.Gupta A, Kelly PA, Bickerton S, Walbran WA. Simulating the effect of temperature elevation on clamping force requirements during rigid-tool Liquid Composite Moulding processes. Compos A Appl Sci Manuf. 2012;43(12):2221–9.CrossRef
  47.Gupta A, Kelly PA, Ehrgott M, Bickerton S. A surrogate model based evolutionary game-theoretic approach for optimizing non-isothermal compression RTM processes. Compos Sci Technol. 2013;29(84):92–100.CrossRef
  48.Advani SG, Hsiao KT, editors. Manufacturing techniques for polymer matrix composites (PMCs). Amsterdam: Elsevier; 2012.
  49.Walbran WA. Experimental validation of local and global force simulations for rigid tool liquid composite moulding processes (Doctoral dissertation, ResearchSpace@ Auckland). 2011.
  50.Jiang S, Ong YS, Zhang J, Feng L. Consistencies and contradictions of performance metrics in multiobjective optimization. IEEE Trans Cybernet. 2014;44(12):2391–404.CrossRef
  51.Hsu S, Ehrgott M, Kelly P. Optimisation of mould filling parameters of the compression resin transfer moulding process. In: 45th annual conference of the operations research society of New Zealand (ORSNZ). 2010 Nov.
  
• 作者单位：Yew-Soon Ong (1)
  Abhishek Gupta (1)
  
  1. School of Computer Engineering, Nanyang Technological University, Singapore, 639798, Singapore
  
• 刊物主题：Neurosciences; Computation by Abstract Devices; Artificial Intelligence (incl. Robotics); Computational Biology/Bioinformatics;
• 出版者：Springer US
• ISSN：1866-9964

文摘

The human mind possesses the most remarkable ability to perform multiple tasks with apparent simultaneity. In fact, with the present-day explosion in the variety and volume of incoming information streams that must be absorbed and appropriately processed, the opportunity, tendency, and (even) the need to multitask are unprecedented. Thus, it comes as little surprise that the pursuit of intelligent systems and algorithms that are capable of efficient multitasking is rapidly gaining importance among contemporary scientists who are faced with the increasing complexity of real-world problems. To this end, the present paper is dedicated to a detailed exposition on a so-far underexplored characteristic of population-based search algorithms, i.e., their inherent ability (much like the human mind) to handle multiple optimization tasks at once. We present a simple evolutionary methodology capable of cross-domain multitask optimization in a unified genotype space and show that there exist many potential benefits of its application in practical domains. Most notably, it is revealed that multitasking enables one to automatically leverage upon the underlying commonalities between distinct optimization tasks, thereby providing the scope for considerably improved performance in real-world problem solving.