A Comparative Analysis of Various Regularization Techniques to Solve Overfitting Problem in Artificial Neural Network

Author:

Gupta Shrikant,Gupta Rajat,Ojha Muneendra,Singh K. P.

Publisher

Springer Singapore

Reference9 articles.

1. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)

2. Smirnov, E.A., Timoshenko, D.M., Andrianov, S.N.: Comparison of regularization methods for imagenet classification with deep convolutional neural networks. AASRI Procedia 6, 89–94 (2014)

3. Lau, K., López, R., Oñate, E.: A neural networks approach to aerofoil noise prediction. In: International Centre Numerical Methods Engineering, vol. CIMNE No-3 (2009)

4. Wan, L., Zeiler, M., Zhang, S., LeCun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: ICML, no. 1, pp. 109–111 (2013)

5. Ng, A.: Feature selection, L1 vs. L2 regularization, and rotational invariance. In: Twenty-First International Conference Machine Learning - ICML 2004, p. 78 (2004)

Cited by 24 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Algorithmic self-referentiality: How machine learning pushes calculative practices to assess themselves;Accounting, Organizations and Society;2024-12

2. Neural Network Design for a Curved Kicking Mechanism with Obstacle Avoidance in RoboCup Small Size League (SSL);Journal of Intelligent & Robotic Systems;2024-08-20

3. Automatic mapping of aquaculture activity in the Atlantic Ocean;International Journal of Applied Earth Observation and Geoinformation;2024-08

4. SCAE—Stacked Convolutional Autoencoder for Fault Diagnosis of a Hydraulic Piston Pump with Limited Data Samples;Sensors;2024-07-18

5. Performance Analysis of Model Optimization Techniques using Pre-Trained CNN Models;2024 IEEE International Conference for Women in Innovation, Technology & Entrepreneurship (ICWITE);2024-02-16

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3