Creative AI Through Evolutionary Computation: Principles and Examples
- 23 March 2021
- journal article
- research article
- Published by Springer Nature in SN Computer Science
- Vol. 2 (3) , 1-7
Abstract
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 make it possible to find creative solutions to practical problems in the real world, making creative AI through evolutionary computation the likely “next deep learning.”Keywords
Funding Information
- Defense Advanced Research Projects Agency (FA8750-18-C-0103)
- National Science Foundation (DBI-0939454)
This publication has 26 references indexed in Scilit:
- Deep learningNature, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- Evolutionary design of discrete controllers for hybrid mechatronic systemsInternational Journal of Systems Science, 2013
- Encouraging Behavioral Diversity in Evolutionary Robotics: An Empirical StudyEvolutionary Computation, 2012
- When Novelty Is Not Enough2011
- Automated synthesis of mechanical vibration absorbers using genetic programmingArtificial Intelligence for Engineering Design, Analysis and Manufacturing, 2008
- A Fast Elitist Non-dominated Sorting Genetic Algorithm for Multi-objective Optimization: NSGA-II2000
- Relative Building-Block Fitness and the Building-Block Hypothesis1993
- A Hierarchical Approach to Learning the Boolean Multiplexer Function1991