Survey on Evolutionary Deep Learning: Principles, Algorithms, Applications, and Open Issues

Abstract

Over recent years, there has been a rapid development of deep learning (DL) in both industry and academia fields. However, finding the optimal hyperparameters of a DL model often needs high computational cost and human expertise. To mitigate the above issue, evolutionary computation (EC) as a powerful heuristic search approach has shown significant merits in the automated design of DL models, so-called evolutionary deep learning (EDL). This paper aims to analyze EDL from the perspective of automated machine learning (AutoML). Specifically, we firstly illuminate EDL from DL and EC and regard EDL as an optimization problem. According to the DL pipeline, we systematically introduce EDL methods ranging from data preparation, model generation, to model deployment with a new taxonomy (i.e., what and how to evolve/optimize), and focus on the discussions of solution representation and search paradigm in handling the optimization problem by EC. Finally, key applications, open issues and potentially promising lines of future research are suggested. This survey has reviewed recent developments of EDL and offers insightful guidelines for the development of EDL.

Residual learning-based robotic image analysis model for low-voltage distributed photovoltaic fault identification and positioning

“…As the network deepens, degradation and gradient vanishing problems may occur, resulting in deep neural networks that are difficult to train. Although many studies have optimized network architectures, the problem has not been fully solved yet ( Li et al, 2023 ). So, residual learning is introduced.…”

A Clustering and Vector Angle-based Adaptive Evolutionary Algorithm for Multi-objective Optimization With Irregular Pareto Fronts

“…Then, the sum of the squared errors between each two clusters is calculated by Eq. (1). It is assumed that after calculation, the sum of squared errors d(C, D) between C and D is minimal, so they are first merged into a new cluster C1.…”

Wear Prediction of Tool Based on Modal Decomposition and MCNN-BiLSTM

“…There may be some information loss when converting signals to frequency or time-frequency domains for analysis. In addition to being adept at watching and finding, researchers also need to have a certain set of abilities and expertise in order to extract characteristics that are highly associated with tool wear state [42]. Additionally, the retrieved characteristics have poor universality and interpretability, and it is possible that more delicate traits were left out.…”