A survey of uncertainty in deep neural networks

人工神经网络 计算机科学 领域(数学) 人工智能 不确定度量化 机器学习 贝叶斯概率 深层神经网络 不确定度分析 数学 模拟 纯数学
作者
Jakob Gawlikowski,Cedrique Rovile Njieutcheu Tassi,Mohsin Ali,Jong‐Seok Lee,Matthias Humt,Jianxiang Feng,Anna Kruspe,Rudolph Triebel,Peter Jung,Ribana Roscher,Muhammad Shahzad,Wen Yang,Richard Bamler,Xiao Xiang Zhu
出处
期刊:Artificial Intelligence Review [Springer Science+Business Media]
卷期号:56 (S1): 1513-1589 被引量:303
标识
DOI:10.1007/s10462-023-10562-9
摘要

Abstract Over the last decade, neural networks have reached almost every field of science and become a crucial part of various real world applications. Due to the increasing spread, confidence in neural network predictions has become more and more important. However, basic neural networks do not deliver certainty estimates or suffer from over- or under-confidence, i.e. are badly calibrated. To overcome this, many researchers have been working on understanding and quantifying uncertainty in a neural network’s prediction. As a result, different types and sources of uncertainty have been identified and various approaches to measure and quantify uncertainty in neural networks have been proposed. This work gives a comprehensive overview of uncertainty estimation in neural networks, reviews recent advances in the field, highlights current challenges, and identifies potential research opportunities. It is intended to give anyone interested in uncertainty estimation in neural networks a broad overview and introduction, without presupposing prior knowledge in this field. For that, a comprehensive introduction to the most crucial sources of uncertainty is given and their separation into reducible model uncertainty and irreducible data uncertainty is presented. The modeling of these uncertainties based on deterministic neural networks, Bayesian neural networks (BNNs), ensemble of neural networks, and test-time data augmentation approaches is introduced and different branches of these fields as well as the latest developments are discussed. For a practical application, we discuss different measures of uncertainty, approaches for calibrating neural networks, and give an overview of existing baselines and available implementations. Different examples from the wide spectrum of challenges in the fields of medical image analysis, robotics, and earth observation give an idea of the needs and challenges regarding uncertainties in the practical applications of neural networks. Additionally, the practical limitations of uncertainty quantification methods in neural networks for mission- and safety-critical real world applications are discussed and an outlook on the next steps towards a broader usage of such methods is given.
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
传奇3应助Xw采纳,获得10
刚刚
1秒前
1秒前
别闹闹发布了新的文献求助10
4秒前
幸运星发布了新的文献求助10
4秒前
CipherSage应助mark采纳,获得10
6秒前
pluto应助从容的香菇采纳,获得10
6秒前
科研通AI5应助cccyq采纳,获得10
7秒前
科研狗完成签到,获得积分10
9秒前
英俊的铭应助gs19960828采纳,获得10
10秒前
MrTStar完成签到 ,获得积分10
12秒前
淡定的惜完成签到,获得积分20
15秒前
完美世界应助fengliurencai采纳,获得10
20秒前
思源应助大面包采纳,获得10
21秒前
sandra完成签到 ,获得积分10
22秒前
iris601完成签到,获得积分10
24秒前
时笙发布了新的文献求助30
26秒前
温柔的迎荷完成签到,获得积分10
28秒前
量子星尘发布了新的文献求助10
30秒前
31秒前
31秒前
传奇3应助快乐一江采纳,获得10
32秒前
传统的纸飞机完成签到 ,获得积分10
32秒前
32秒前
32秒前
王子安应助lilila666采纳,获得10
34秒前
大面包发布了新的文献求助10
35秒前
情怀应助漫山采纳,获得10
36秒前
zzz完成签到,获得积分10
37秒前
gs19960828发布了新的文献求助10
38秒前
幸福大白发布了新的文献求助30
38秒前
脑洞疼应助jbhb采纳,获得10
42秒前
42秒前
gs19960828完成签到,获得积分10
43秒前
Younglee完成签到,获得积分10
47秒前
47秒前
xiaoxuan完成签到,获得积分10
48秒前
49秒前
Garnieta完成签到,获得积分10
50秒前
彤光赫显发布了新的文献求助10
51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 3989406
求助须知:如何正确求助?哪些是违规求助? 3531522
关于积分的说明 11254187
捐赠科研通 3270174
什么是DOI,文献DOI怎么找? 1804901
邀请新用户注册赠送积分活动 882105
科研通“疑难数据库(出版商)”最低求助积分说明 809174