Survey of continuous deep learning methods and techniques used for incremental learning

计算机科学 人工智能 渐进式学习 深度学习 机器学习
作者
Justin Leo,Jugal Kalita
出处
期刊:Neurocomputing [Elsevier BV]
卷期号:582: 127545-127545 被引量:7
标识
DOI:10.1016/j.neucom.2024.127545
摘要

Neural networks and deep learning algorithms are designed to function similarly to biological synaptic structures. However, classical deep learning algorithms fail to fully capture the need for continuous learning; this has led to the advent of incremental learning. Incremental learning adds new challenges that are handled differently by modern state-of-the-art approaches. Some of these include: utilization of network memory as additional knowledge increases the size of the network, open-set recognition to be able to identify unrecognized information, and efficient knowledge distillation as most incremental learning algorithms are prone to catastrophic forgetting of previously learned knowledge. Recent advancements achieve incremental learning through a multitude of methods. Most methods are characterized by augmenting the normal algorithm of neural network training by both directly modifying the neural network structure and by adding additional learning steps. This paper analyzes and provides a comprehensive survey of existing methods and various techniques used for incremental learning. A novel categorization of the methods is also introduced based on recent trends of the state-of-the-art solutions. The study focuses on methods that provide incremental learning success as well as discusses emerging patterns in new research.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
鱼e完成签到,获得积分10
1秒前
1秒前
2秒前
2秒前
song发布了新的文献求助10
4秒前
ding应助时尚初之采纳,获得10
4秒前
罗拉完成签到,获得积分10
4秒前
4秒前
5秒前
yun尘世完成签到,获得积分10
6秒前
6秒前
自信南霜完成签到,获得积分10
6秒前
tingting9完成签到,获得积分10
9秒前
9秒前
10秒前
卡布奇诺完成签到,获得积分10
10秒前
13223456发布了新的文献求助10
10秒前
青山落日秋月春风完成签到,获得积分10
12秒前
13秒前
14秒前
14秒前
小马甲应助动听的雅绿采纳,获得30
15秒前
1177发布了新的文献求助10
17秒前
17秒前
喜喵喵完成签到,获得积分10
18秒前
18秒前
18秒前
18秒前
11关注了科研通微信公众号
19秒前
123456完成签到,获得积分10
20秒前
时尚初之发布了新的文献求助10
20秒前
ddd完成签到,获得积分10
21秒前
喜喵喵发布了新的文献求助10
23秒前
无情的函发布了新的文献求助10
23秒前
麦乐迪完成签到 ,获得积分10
24秒前
SYLH应助云横秦岭家何在采纳,获得10
24秒前
bkagyin应助如意枫叶采纳,获得10
25秒前
科目三应助Quinna采纳,获得10
25秒前
25秒前
彭栋发布了新的文献求助10
25秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989242
求助须知:如何正确求助?哪些是违规求助? 3531393
关于积分的说明 11253753
捐赠科研通 3270010
什么是DOI,文献DOI怎么找? 1804868
邀请新用户注册赠送积分活动 882084
科研通“疑难数据库(出版商)”最低求助积分说明 809136