Evolutionary Computation Meets Machine Learning: A Survey

By Jun Zhang, Zhi-hui Zhan, Ying Lin, Ni Chen, Yue-jiao Gong, J. Zhong, Henry Shu-Hung Chung, Yun Li, Yu-hui Shi. 2011

269 citations recorded by the source corpus.

Evolutionary computation (EC) is a kind of optimization methodology inspired by the mechanisms of biological evolution and behaviors of living organisms. In the literature, the terminology evolutionary algorithms is frequently treated the same as EC. This article focuses on making a survey of researches based on using ML techniques to enhance EC algorithms. In the framework of an ML-technique enhanced-EC algorithm (MLEC), the main idea is that the EC algorithm has stored ample data about the search space, problem features, and population information during the iterative search process, thus the ML technique is helpful in analyzing these data for enhancing the search performance. The paper presents a survey of five categories: ML for population initialization, ML for fitness evaluation and selection, ML for population reproduction and variation, ML for algorithm adaptation, and ML for local search.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

Population Based Training of Neural Networks (2017, methodology): “This mixture of learning and evolutionary-like algorithms has also been explored successfully in other domains (Zhang et al., 2011) such as neural architecture search (Real et al., 2017; Liu et al., 2017), feature selection (Xue et al., 2016), and parameter learning (Fernando et al., 2016).”
Cloud Computing Resource Scheduling and a Survey of Its Evolutionary Approaches (2015, background): “However, as cloud scheduling can face challenges of a high volume, velocity, and variety of data arriving during the runtime, a more efﬁcient use of search information and problem information during the evolutionary process should be explored [Zhang et al. 2011c; Zhan et al. ].”
Artificial intelligence and machine learning approaches to energy demand-side response: A systematic review (2020, background): “programming (GP), learning classifier systems (LCS), differential evolution (DE), and estimation of distribution algorithm (EDA) [129].”
An Overview of Artificial Intelligence Applications for Power Electronics (2020, methodology): “For more theoretical details of the metaheuristic methods, readers can refer to [16] and [78].”
muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems (2022, methodology): “The automation of hyperparameter tuning has been commonly addressed with Bayesian optimization [Srinivas et al., 2010, Bergstra et al., 2011, Snoek et al., 2012], evolutionary methods have also been explored [Jaderberg et al., 2017, Zhang et al., 2011].”
Edge Computing with Artificial Intelligence: A Machine Learning Perspective (2022, methodology): “After that, the evolutionary algorithms continuously iterate three steps named itness evaluation and selection, population reproduction and variation, and population updating [82].”
Techniques for Automated Machine Learning (2019, background): “Evolutionary algorithm (EA) [99] finds the optimal solution from the mutation of random initial individuals, just like the natural evolution.”
Multiple Populations for Multiple Objectives: A Coevolutionary Technique for Solving Multiobjective Optimization Problems (2013, methodology): “1) applying other algorithms like GA [59], [60], ant colony optimization [61]–[63], DE [64]–[67], EDA, MA [68]–[72], and their improved variants (like enhanced PSO variants [73]–[76])”