摘要
当数据规模庞大时,深度学习模型会遇到权重调整耗时,容易陷入局部最优解的问题。为了解决这些问题,宽度学习系统应运而生,宽度学习系统不仅结构简单、训练速度快、准确率高,而且还具有增量学习的优势。介绍了宽度学习系统的产生背景和发展历程,阐述了宽度学习系统的基础理论与实现方法,对比了它与深度网络的异同;介绍了宽度学习系统在图像分类、数值回归、脑电信号处理等应用中的改进算法,分析了这些算法的优势和不足。最后总结了现有宽度学习算法存在的缺陷,并对未来研究方向进行了展望。
When the scale of data is large,the deep learning model will encounter the problem of time-consuming weight adjustment and easy to fall into the local optimal solution.In order to solve these problems,broad learning system comes into being.The broad learning system not only has the advantages of simple structure,fast training speed and high accuracy,but also has the advantage of incremental learning.This paper firstly introduced the background and development of broad learning system,then described the basic theory and implementation method of broad learning system,and compared its similarities and differences with deep network.Then this paper introduced the improvement of broad learning system on image classification,numerical regression,EEG signal processing,and analyzed the advantages and disadvantages of these algorithms.Finally,it summarized the shortcomings of existing broad learning algorithms,and prospected the future research direction.
作者
任长娥
袁超
孙彦丽
刘竹琳
陈俊龙
Ren Chang’e;Yuan Chao;Sun Yanli;Liu Zhulin;CLPhilip Chen(College of Information Engineering,Capital Normal University,Beijing 100048,China;School of Computer Science&Engineering,South China University of Technology,Guangzhou 510006,China)
出处
《计算机应用研究》
CSCD
北大核心
2021年第8期2258-2267,共10页
Application Research of Computers
基金
国家自然科学基金项目(61803276,61751202,U1813203)
北京市教育委员会科技计划一般项目(KM201910028004)
北京市自然科学基金项目(4202011)
澳门科技发展基金委项目(079/2017/A2,024/2015/AMJ,0119/2018/A3)。
关键词
宽度学习系统
神经网络
深度学习
图像分类
增量学习
broad learning system
neural network
deep learning
image classification
incremental learning
