A Review of Deep Learning Models Based on Neuroevolution

HAN Chong; WANG Jun-li; WU Yu-xi; ZHANG Chao-bo

doi:10.12263/DZXB.20200139

您当前的位置：

首页 >

文章列表页 >

A Review of Deep Learning Models Based on Neuroevolution

更新时间：2025-12-08

- A Review of Deep Learning Models Based on Neuroevolution
- Acta Electronica Sinica Vol. 49, Issue 2, Pages: 372-379(2021)
- 作者机构：
  
  同济大学电子与信息工程学院,上海,201804
- 作者简介：
- 基金信息：
  
  National Key Research and Development Program of China (No.2017YFA0700602);National Natural Science Foundation of China (No.61672381);Fundamental Research Funds for the Central Universities(2022XKRC015)
- DOI：10.12263/DZXB.20200139
  CLC： TP391.4
- Published Online：25 February 2021，
  
  Published：2021
- 稿件说明：
移动端阅览
HAN Chong, WANG Jun-li, WU Yu-xi, et al. A Review of Deep Learning Models Based on Neuroevolution[J]. Acta Electronica Sinica, 2021, 49(2): 372-379.
DOI：

HAN Chong, WANG Jun-li, WU Yu-xi, et al. A Review of Deep Learning Models Based on Neuroevolution[J]. Acta Electronica Sinica, 2021, 49(2): 372-379. DOI： 10.12263/DZXB.20200139.

摘要

深度学习研究发展至今已可以胜任各类识别、分类、生成任务，但是对于不同的任务，神经网络的结构或参数不可能只是微小的变化，依然需要专家进行调整.在这样的情况下，自动化地调整神经网络的结构或参数成为研究热点.其中，以达尔文自然进化论为灵感的神经进化成为主要优化方法.利用神经进化优化的深度学习模型以种群为基础，通过突变、重组等操作进化，可实现自动地、逐步地构建神经网络并最终选择出性能最优的深度学习模型.本文简述了神经进化与进化计算；详细概述了各类基于神经进化的深度学习模型；分析了各类模型的性能；总结了神经进化与深度学习融合的前景并探讨下一步的研究方向.

Abstract

With the development of deep learning

it has been competent to various types of tasks

such as identification

classification

and generation. However

the structures or parameters of artificial neural networks cannot be only a little changed for different task

experts need to adjust the structures or parameters of the neural network. In such situations

the method of automatically adjusting the structures or parameters of the artificial neural network has become a research hotspot

among these methods

neuroevolution inspired by Darwin's natural evolution theory has become the main optimization method for that. Deep learning models optimized by neuroevolution based on population

evolving through mutation

crossover and other operations

can automatically and gradually construct the neural network and then choose the most optimal deep learning model. This paper summarizes the neuroevolution and the evolutionary computation. It elaborates various deep learning models based on neuroevolution

and analyzes the performance of these models. It concludes prospects of the deep learning model based on neuroevolution and discusses the next research directions.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

SeqGANPass: Password Guessing with Sequence Generative Adversarial Nets

Feature-Space Optimization-Inspired and Self-Attention Enhanced Neural Network Reconstruction Algorithm for Image Compressive Sensing

Research and Challenges of Medical Image Landmark Detection Based on Deep Learning

RGB-D Scene Parsing Based on Spatial Structured Inference Deep Fusion Networks

Related Author

GONG Xue-luan

CHEN Yan-jiao

WANG Tao

CAO Yu-xin

CHEN Wen-jun

YANG Chun-ling

WANG Ying-hui

LI Gang

Related Institution

College of Computer Science， Wuhan University， Wuhuan

College of Electrical Engineering， Zhejiang University

School of Electronic and Information Engineering, South China University of Technology

Peking University School of Stomatology

School of Electronic and Information Engineering, Beijing Jiaotong University

⁰