A biological perspective on evolutionary computation

Evolutionary computation is inspired by the mechanisms of biological evolution. With algorithmic improvements and increasing computing resources, evolutionary computation has discovered creative and innovative solutions to challenging practical problems. This paper evaluates how today’s evolutionary computation compares to biological evolution and how it may fall short. A small number of well-accepted characteristics of biological evolution are considered: openendedness, major transitions in organizational structure, neutrality and genetic drift, multi-objectivity, complex genotype-to-phenotype mappings and co-evolution. Evolutionary computation exhibits many of these to some extent but more can be achieved by scaling up with available computing and by emulating biology more carefully. In particular, evolutionary computation diverges from biological evolution in three key respects: it is based on small populations and strong selection; it typically uses direct genotype-to-phenotype mappings; and it does not achieve major organizational transitions. These shortcomings suggest a roadmap for future evolutionary computation research, and point to gaps in our understanding of how biology discovers major transitions. Advances in these areas can lead to evolutionary computation that approaches the complexity and flexibility of biology, and can serve as an executable model of biological processes. Evolutionary computation is inspired by biological evolution and exhibits characteristics familiar from biology such as openendedness, multi-objectivity and co-evolution. This Perspective highlights where major differences still exist, and where the field of evolutionary computation could attempt to approach features from biological evolution more closely, namely neutrality and random drift, complex genotype-to-phenotype mappings with rich environmental interactions and major organizational transitions.

[1]  Elliot Meyerson,et al.  Flavor-cyber-agriculture: Optimization of plant metabolites in an open-source control environment through surrogate modeling , 2018, bioRxiv.

[2]  A. V. Napalkov,et al.  COMPUTERS AND THOUGHT, EDITED BY E. A. FEIGENBAUM AND J. FELDMAN, NEW YORK, MCGRAW-HILL, 1963: BOOK REVIEW, , 1967 .

[3]  Carole-Jean Wu,et al.  GEVO: GPU Code Optimization using Evolutionary Computation , 2020, ACM Trans. Archit. Code Optim..

[4]  Kalyanmoy Deb,et al.  An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point-Based Nondominated Sorting Approach, Part I: Solving Problems With Box Constraints , 2014, IEEE Transactions on Evolutionary Computation.

[5]  R. Lenski,et al.  Pervasive compensatory adaptation in Escherichia coli , 2000, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[6]  Claire Le Goues,et al.  A systematic study of automated program repair: Fixing 55 out of 105 bugs for $8 each , 2012, 2012 34th International Conference on Software Engineering (ICSE).

[7]  Risto Miikkulainen,et al.  Competitive Coevolution through Evolutionary Complexification , 2011, J. Artif. Intell. Res..

[8]  Demis Hassabis,et al.  A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play , 2018, Science.

[9]  A. Wagner.  Robustness, evolvability, and neutrality , 2005, FEBS letters.

[10]  Risto Miikkulainen,et al.  The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities , 2018, Artificial Life.

[11]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[12]  Jason H. Moore,et al.  A Probabilistic and Multi-Objective Analysis of Lexicase Selection and ε-Lexicase Selection , 2019, Evolutionary Computation.

[13]  Risto Miikkulainen,et al.  Adaptive Control Utilising Neural Swarming , 2002, GECCO.

[14]  A. Gardner,et al.  Major evolutionary transitions in individuality , 2015, Proceedings of the National Academy of Sciences.

[15]  Hans-Paul Schwefel,et al.  Evolution strategies – A comprehensive introduction , 2002, Natural Computing.

[16]  Hod Lipson,et al.  Distilling Free-Form Natural Laws from Experimental Data , 2009, Science.

[17]  Gregory Gutin,et al.  A New Approach to Population Sizing for Memetic Algorithms: A Case Study for the Multidimensional Assignment Problem , 2010, Evolutionary Computation.

[18]  Jason H. Moore,et al.  Robustness, Evolvability, and the Logic of Genetic Regulation , 2014, Artificial Life.

[19]  Risto Miikkulainen,et al.  Open-ended behavioral complexity for evolved virtual creatures , 2013, GECCO '13.

[20]  Hod Lipson,et al.  Scalable co-optimization of morphology and control in embodied machines , 2017, Journal of The Royal Society Interface.

[21]  Penousal Machado,et al.  The Art of Artificial Evolution , 2008 .

[22]  Phil Husbands,et al.  Neutral Networks and Evolvability with Complex Genotype-Phenotype Mapping , 2001, ECAL.

[23]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[24]  Peter J. Bentley,et al.  Evolving Fractal Gene Regulatory Networks for Robot Control , 2003, ECAL.

[25]  Xin Yao,et al.  Evolutionary Generative Adversarial Networks , 2018, IEEE Transactions on Evolutionary Computation.

[26]  H. Hendriks-Jansen.  Catching Ourselves in the Act: Situated Activity, Interactive Emergence, Evolution, and Human Thought , 1996 .

[27]  L. Darrell Whitley,et al.  Adding Learning to the Cellular Development of Neural Networks: Evolution and the Baldwin Effect , 1993, Evolutionary Computation.

[28]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[29]  Symbiosis Promotes Fitness Improvements in the Game of Life , 2020, Artificial Life.

[30]  Kalyanmoy Deb,et al.  Improving the performance of genetic algorithms for land-use allocation problems , 2018, Int. J. Geogr. Inf. Sci..

[31]  L. H. Liow,et al.  Red Queen: from populations to taxa and communities. , 2011, Trends in ecology & evolution.

[32]  Zbigniew Michalewicz,et al.  Evolutionary Algorithms in Engineering Applications , 1997, Springer Berlin Heidelberg.

[33]  John Holland,et al.  Adaptation in Natural and Artificial Sys-tems: An Introductory Analysis with Applications to Biology , 1975 .

[34]  Kenneth O. Stanley and Jeff Clune and Joel Lehman and Rist Miikkulainen,et al.  Designing Neural Networks through Evolutionary Algorithms , 2019 .

[35]  A. Tate.  A measure of intelligence , 2012 .

[36]  A. Wagner.  Robustness and Evolvability in Living Systems , 2005 .

[37]  A. Maritan,et al.  Neutral and niche forces as drivers of species selection. , 2019, Journal of theoretical biology.

[38]  Jason H. Moore,et al.  Solution and Fitness Evolution (SAFE): Coevolving Solutions and Their Objective Functions , 2019, EuroGP.

[39]  Saman P. Amarasinghe,et al.  Meta optimization: improving compiler heuristics with machine learning , 2003, PLDI '03.

[40]  Handing Wang,et al.  Data-Driven Surrogate-Assisted Multiobjective Evolutionary Optimization of a Trauma System , 2016, IEEE Transactions on Evolutionary Computation.

[41]  Kenneth O. Stanley,et al.  Why Greatness Cannot Be Planned , 2015, Springer International Publishing.

[42]  Lee Spector,et al.  Genetic Programming and Autoconstructive Evolution with the Push Programming Language , 2002, Genetic Programming and Evolvable Machines.

[43]  Ian C. Parmee,et al.  Evolutionary and adaptive computing in engineering design , 2001 .

[44]  David E. Goldberg,et al.  Genetic Algorithms with Sharing for Multimodalfunction Optimization , 1987, ICGA.

[45]  Bart Deplancke,et al.  Gene Regulatory Networks , 2012, Methods in Molecular Biology.

[46]  Samir W. Mahfoud.  Niching methods for genetic algorithms , 1996 .

[47]  Risto Miikkulainen,et al.  Constructing competitive and cooperative agent behavior using coevolution , 2010, CIG.

[48]  Edwin D. de Jong,et al.  Ideal Evaluation from Coevolution , 2004, Evolutionary Computation.

[49]  M. Lind,et al.  Evolutionary consequences of epigenetic inheritance , 2018, Heredity.

[50]  Christoph Adami,et al.  Different Evolutionary Paths to Complexity for Small and Large Populations of Digital Organisms , 2016, bioRxiv.

[51]  S Forrest,et al.  Genetic algorithms , 1996, CSUR.

[52]  Dan S. Tawfik,et al.  Robustness–epistasis link shapes the fitness landscape of a randomly drifting protein , 2006, Nature.

[53]  W. Daniel Hillis,et al.  Co-evolving parasites improve simulated evolution as an optimization procedure , 1990 .

[54]  E. Szathmáry.  Toward major evolutionary transitions theory 2.0 , 2015, Proceedings of the National Academy of Sciences.

[55]  Kenneth O. Stanley,et al.  Picbreeder: A Case Study in Collaborative Evolutionary Exploration of Design Space , 2011, Evolutionary Computation.

[56]  Eric Smith,et al.  Universality in intermediary metabolism. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[57]  Thomas S. Ray,et al.  An Approach to the Synthesis of Life , 1991 .

[58]  Kenneth O. Stanley.  Why Open-Endedness Matters , 2019, Artificial Life.

[59]  Eörs Szathmáry,et al.  The Major Transitions in Evolution , 1997 .

[60]  Cezary Z. Janikow,et al.  A survey of modularity in genetic programming , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[61]  Jordan B. Pollack,et al.  Pareto Optimality in Coevolutionary Learning , 2001, ECAL.

[62]  C. Adami,et al.  Evolution of drift robustness in small populations , 2016, Nature Communications.

[63]  Sai Ho Ling,et al.  Evolutionary Algorithms in Health Technologies , 2019, Algorithms.

[64]  Lee Spector,et al.  Division blocks and the open-ended evolution of development, form, and behavior , 2007, GECCO '07.

[65]  Kenneth O. Stanley,et al.  Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning , 2017, ArXiv.

[66]  Alok Aggarwal,et al.  Regularized Evolution for Image Classifier Architecture Search , 2018, AAAI.

[67]  ForrestStephanie,et al.  Post-compiler software optimization for reducing energy , 2014 .

[68]  Jacques Periaux,et al.  Evolutionary algorithms and metaheuristics: applications in engineering design and optimization , 2018 .

[69]  Andrew P. Hendry,et al.  Speciation without Pre-Defined Fitness Functions , 2015, PloS one.

[70]  Christin Wirth,et al.  Blondie24 Playing At The Edge Of Ai , 2016 .

[71]  Gabriela Ochoa,et al.  Modelling genetic improvement landscapes with local optima networks , 2017, GECCO.

[72]  Kenneth O. Stanley,et al.  POET: open-ended coevolution of environments and their optimized solutions , 2019, GECCO.

[73]  John S. McCaskill,et al.  Open Problems in Artificial Life , 2000, Artificial Life.

[74]  U. Dieckmann,et al.  On the origin of species by sympatric speciation , 1999, Nature.

[75]  Matthew C. Cowperthwaite,et al.  From Bad to Good: Fitness Reversals and the Ascent of Deleterious Mutations , 2006, PLoS Comput. Biol..

[76]  Risto Miikkulainen,et al.  Acquiring evolvability through adaptive representations , 2007, GECCO '07.

[77]  Benoit Baudry,et al.  A journey among Java neutral program variants , 2019, Genetic Programming and Evolvable Machines.

[78]  G. Müller.  Evo–devo: extending the evolutionary synthesis , 2007, Nature Reviews Genetics.

[79]  Peter Nordin,et al.  Genetic programming - An Introduction: On the Automatic Evolution of Computer Programs and Its Applications , 1998 .

[80]  M. M. Makela,et al.  Evolutionary Algorithms in Engineering and Computer Science: Recent Advances in Genetic Algorithms, Evolution Strategies, Evolutionary Programming, Genetic Programming and Industrial Applications , 1999 .

[81]  Jeff Clune,et al.  Improving HybrID: How to best combine indirect and direct encoding in evolutionary algorithms , 2017, PloS one.

[82]  Qian Wang,et al.  Epigenetic game theory: How to compute the epigenetic control of maternal-to-zygotic transition. , 2017, Physics of life reviews.

[83]  Elliot Meyerson,et al.  Evolving Deep Neural Networks , 2017, Artificial Intelligence in the Age of Neural Networks and Brain Computing.

[84]  Risto Miikkulainen,et al.  Accelerated Neural Evolution through Cooperatively Coevolved Synapses , 2008, J. Mach. Learn. Res..

[85]  Westley Weimer,et al.  Software mutational robustness , 2012, Genetic Programming and Evolvable Machines.

[86]  Westley Weimer,et al.  Neutrality and epistasis in program space , 2018, GI@ICSE.

[87]  Jason D. Lohn,et al.  Computer-Automated Evolution of an X-Band Antenna for NASA's Space Technology 5 Mission , 2011, Evolutionary Computation.

[88]  M. Kimura,et al.  The neutral theory of molecular evolution. , 1983, Scientific American.

[89]  Elliot Meyerson,et al.  Evolutionary neural AutoML for deep learning , 2019, GECCO.

[90]  G. Wagner,et al.  Mutational robustness can facilitate adaptation , 2010, Nature.

[91]  C. Ofria,et al.  Genome complexity, robustness and genetic interactions in digital organisms , 1999, Nature.

[92]  Julian Francis Miller,et al.  Through the Interaction of Neutral and Adaptive Mutations, Evolutionary Search Finds a Way , 2006, Artificial Life.

[93]  J. Miller,et al.  Guidelines: From artificial evolution to computational evolution: a research agenda , 2006, Nature Reviews Genetics.

[94]  Susan Stepney,et al.  Defining and simulating open-ended novelty: requirements, guidelines, and challenges , 2016, Theory in Biosciences.

[95]  Kaisa Miettinen,et al.  Evolutionary algorithms in engineering and computer science : recent advances in genetic algorithms, evolution strategies, evolutionary programming, genetic programming and industrial applications , 1999 .

[96]  E. Davidson,et al.  Gene regulatory networks. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[97]  L. Darrell Whitley,et al.  The massively parallel mixing genetic algorithm for the traveling salesman problem , 2019, GECCO.

[98]  Kenneth A. De Jong,et al.  Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents , 2000, Evolutionary Computation.

[99]  Claire Le Goues,et al.  GenProg: A Generic Method for Automatic Software Repair , 2012, IEEE Transactions on Software Engineering.

[100]  Gary B. Lamont,et al.  Evolutionary Algorithms for Solving Multi-Objective Problems , 2002, Genetic Algorithms and Evolutionary Computation.

[101]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[102]  Wolfgang Banzhaf,et al.  Evolution on Neutral Networks in Genetic Programming , 2006 .

[103]  E. Davidson,et al.  Gene Regulatory Networks and the Evolution of Animal Body Plans , 2006, Science.

[104]  Jacob Schrum,et al.  Comparing direct and indirect encodings using both raw and hand-designed features in tetris , 2017, GECCO.

[105]  R. Miikkulainen,et al.  Learning Behavior Characterizations for Novelty Search , 2016, GECCO.

[106]  Eduardo Miranda,et al.  Evolutionary Computer Music , 2007 .

[107]  John H. Holland,et al.  Outline for a Logical Theory of Adaptive Systems , 1962, JACM.

[108]  Kenneth O. Stanley,et al.  A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks , 2009, Artificial Life.

[109]  Yong Hu,et al.  Application of evolutionary computation for rule discovery in stock algorithmic trading: A literature review , 2015, Appl. Soft Comput..

[110]  M. Lynch.  The frailty of adaptive hypotheses for the origins of organismal complexity , 2007, Proceedings of the National Academy of Sciences.

[111]  Horst Hendriks-Jansen,et al.  Catching ourselves in the act , 1996 .

[112]  Westley Weimer,et al.  Post-compiler software optimization for reducing energy , 2014, ASPLOS.

[113]  J. Pollack,et al.  A computational model of symbiotic composition in evolutionary transitions. , 2003, Bio Systems.

[114]  Risto Miikkulainen,et al.  Designing neural networks through neuroevolution , 2019, Nat. Mach. Intell..

[115]  Nikolaus Hansen,et al.  The CMA Evolution Strategy: A Tutorial , 2016, ArXiv.

[116]  B. Levin,et al.  Compensatory mutations, antibiotic resistance and the population genetics of adaptive evolution in bacteria. , 2000, Genetics.

[117]  Stefano Nolfi,et al.  Robustness to Faults Promotes Evolvability: Insights from Evolving Digital Circuits , 2016, PloS one.

[118]  Kenneth O. Stanley,et al.  Confronting the Challenge of Quality Diversity , 2015, GECCO.

[119]  Vidroha Debroy,et al.  Genetic Programming , 1998, Lecture Notes in Computer Science.