A Study of the Effect of Noise Injection on the Training of Artificial Neural Networks

被引：0

作者：

Jiang, Yulei ^{[1
]}

Zur, Richard M. ^{[1
]}

Pesce, Lorenzo L. ^{[1
]}

Drukker, Karen ^{[1
]}

机构：

[1] Univ Chicago, Dept Radiol, Chicago, IL 60637 USA

来源：

IJCNN: 2009 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1- 6 | 2009年

关键词：

COMPUTER-AIDED DIAGNOSIS; MAXIMUM-LIKELIHOOD-ESTIMATION; SCREENING MAMMOGRAPHY; ROC CURVES; PERFORMANCE;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We studied the effect of noise injection in overcoming the problem of overtraining in the training of artificial neural networks (ANNs) in comparison with other common approaches for overcoming this problem such as early stopping of the ANN training process and weight decay (which is similar to Bayesian artificial neural networks). We found from simulation studies and studies of a computer-aided diagnosis application that noise injection is effective in overcoming overtraining and is as effective as, or even more effective than, early stopping and weight decay.

引用

页码：2784 / 2788

页数：5

共 50 条

[21] On the application of artificial neural networks for the prediction of NOxemissions from a high-speed direct injection diesel engine
Fang, XiaoHang
Papaioannou, Nick
Leach, Felix
Davy, Martin H.
INTERNATIONAL JOURNAL OF ENGINE RESEARCH, 2021, 22 (06) : 1808 - 1824
[22] Using artificial neural networks to enhance CART
Young, William A., II
Weckman, Gary R.
Hari, Vijaya
Whiting, Harry S., II
Snow, Andrew P.
NEURAL COMPUTING & APPLICATIONS, 2012, 21 (07) : 1477 - 1489
[23] The structure dilemma in biological and artificial neural networks
Pircher, Thomas
Pircher, Bianca
Schluecker, Eberhard
Feigenspan, Andreas
SCIENTIFIC REPORTS, 2021, 11 (01)
[24] Artificial neural networks approach on vibration and noise parameters assessment of flaxseed oil biodiesel fuelled CI engine
Jaikumar, S.
Srinivas, V.
Satyanarayana, M. R. S.
Rajasekhar, M.
Vamsi Teja, D.
Tej Kamal, Ch.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY, 2021, 18 (08) : 2365 - 2376
[25] Medical image analysis with artificial neural networks
Jiang, J.
Trundle, P.
Ren, J.
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2010, 34 (08) : 617 - 631
[26] Convergence Analysis of Multiplicative Weight Noise Injection During Training
Ho, Kevin
Leung, Chi-Sing
Sum, John
Lau, Siu-Chung
INTERNATIONAL CONFERENCE ON TECHNOLOGIES AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE (TAAI 2010), 2010, : 358 - 365
[27] Artificial neural network approach to investigate the effect of injection pressure and timing on diesel engine fuelled with diestrol
Kannan, G. R.
INTERNATIONAL JOURNAL OF OIL GAS AND COAL TECHNOLOGY, 2016, 11 (02) : 154 - 179
[28] Artificial Noise Injection-Based Secrecy Improvement for FSO Systems
Sikri, Aman
Mathur, Aashish
Bhatnagar, Manav
Kaddoum, Georges
Saxena, Prakriti
Nebhen, Jamel
IEEE PHOTONICS JOURNAL, 2021, 13 (02):
[29] An emotional artificial neural network for prediction of vehicular traffic noise
Nourani, Vahid
Gokcekus, Huseyin
Umar, Ibrahim Khalil
Najafi, Hessam
SCIENCE OF THE TOTAL ENVIRONMENT, 2020, 707
[30] Clipping Noise Compensation with Neural Networks in OFDM Systems
Sang, Tzu-Hsien
Xu, You-Cheng
SIGNALS, 2020, 1 (01):

← 1 2 3 4 5 →