Creative AI Through Evolutionary Computation: Principles and Examples

The main power of artificial intelligence is not in modeling what we already know, but in creating solutions that are new. Such solutions exist in extremely large, high-dimensional, and complex search spaces. Population-based search techniques, i.e. variants of evolutionary computation, are well suited to finding them. These techniques are also well positioned to take advantage of large-scale parallel computing resources, making creative AI through evolutionary computation the likely “next deep learning”.

[1]  Risto Miikkulainen,et al.  Sentient Ascend: AI-Based Massively Multivariate Conversion Rate Optimization , 2018, AAAI.

[2]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[3]  Young Joon Park,et al.  Coronavirus Disease Outbreak in Call Center, South Korea , 2020, Emerging infectious diseases.

[4]  P. Mahadevan,et al.  An overview , 2007, Journal of Biosciences.

[5]  Xi Chen,et al.  Evolution Strategies as a Scalable Alternative to Reinforcement Learning , 2017, ArXiv.

[6]  Risto Miikkulainen,et al.  Cultural enhancement of neuroevolution , 2002 .

[7]  Risto Miikkulainen,et al.  Ascend by Evolv: AI-Based Massively Multivariate Conversion Rate Optimization , 2020, AI Mag..

[8]  Arielle J. Johnson,et al.  Flavor-Cyber-Agriculture: Optimization of plant metabolites in an open-source control environment through surrogate modeling , 2018 .

[9]  John R. Koza,et al.  A Hierarchical Approach to Learning the Boolean Multiplexer Function , 1990, FOGA.

[10]  Kalyanmoy Deb,et al.  A population-based fast algorithm for a billion-dimensional resource allocation problem with integer variables , 2017, Eur. J. Oper. Res..

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

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

[13]  H. P. D. Vladar.  Why Greatness Cannot Be Planned: The Myth of the Objective , 2016 .

[14]  Jianjun Hu,et al.  Automated synthesis of mechanical vibration absorbers using genetic programming , 2008, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

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

[16]  Kenneth O. Stanley,et al.  On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent , 2017, ArXiv.

[17]  Elliot Meyerson,et al.  Discovering evolutionary stepping stones through behavior domination , 2017, GECCO.

[18]  Stéphane Doncieux,et al.  Encouraging Behavioral Diversity in Evolutionary Robotics: An Empirical Study , 2012, Evolutionary Computation.

[19]  Tom Schaul,et al.  Rainbow: Combining Improvements in Deep Reinforcement Learning , 2017, AAAI.

[20]  Kenneth O. Stanley,et al.  Revising the evolutionary computation abstraction: minimal criteria novelty search , 2010, GECCO '10.

[21]  Anders Lyhne Christensen,et al.  Devising Effective Novelty Search Algorithms: A Comprehensive Empirical Study , 2015, GECCO.

[22]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[23]  R. Hersh.  Novelty Wins, “Straight Toward Objective” Loses! or Book Review: Why Greatness Cannot Be Planned: The Myth of the Objective, by Kenneth O. Stanley and Joel Lehman , 2015 .

[24]  Risto Miikkulainen,et al.  Enhanced optimization with composite objectives and novelty pulsation , 2019, GECCO.

[25]  Christian L. Althaus,et al.  Dynamic interventions to control COVID-19 pandemic: a multivariate prediction modelling study comparing 16 worldwide countries , 2020, European Journal of Epidemiology.

[26]  Kalyanmoy Deb,et al.  A Fast Elitist Non-dominated Sorting Genetic Algorithm for Multi-objective Optimisation: NSGA-II , 2000, PPSN.

[27]  Risto Miikkulainen,et al.  Enhanced Optimization with Composite Objectives and Novelty Pulsation , 2018, GPTP.

[28]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[29]  Erik D. Goodman,et al.  Evolutionary design of discrete controllers for hybrid mechatronic systems , 2015, Int. J. Syst. Sci..

[30]  Risto Miikkulainen,et al.  Conversion rate optimization through evolutionary computation , 2017, GECCO.

[31]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[32]  Lijun Wu,et al.  Achieving Human Parity on Automatic Chinese to English News Translation , 2018, ArXiv.

[33]  Elliot Meyerson,et al.  Effective reinforcement learning through evolutionary surrogate-assisted prescription , 2020, GECCO.

[34]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

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

[36]  Faustino J. Gomez,et al.  When Novelty Is Not Enough , 2011, EvoApplications.

[37]  Elliot Meyerson,et al.  From Prediction to Prescription: Evolutionary Optimization of Nonpharmaceutical Interventions in the COVID-19 Pandemic , 2020, IEEE Transactions on Evolutionary Computation.

[38]  Melanie Mitchell,et al.  Relative Building-Block Fitness and the Building Block Hypothesis , 1992, FOGA.