Optimization Under Uncertainty Explains Empirical Success of Deep Learning Heuristics

Author:

Kreinovich Vladik,Kosheleva Olga

Publisher

Springer International Publishing

Reference19 articles.

1. Aczel, J., Dhombres, J.: Functional Equations in Several Variables. Cambridge University Press, New York (2008)

2. Autchariyapanitkul, K., Kosheleva, O., Kreinovich, V., Sriboonchitta, S.: Quantum econometrics: how to explain its quantitative successes and how the resulting formulas are related to scale invariance, entropy, and fuzziness. In: Huynh, V.-N., Inuiguchi, M., Tran, D.-H., Denoeux, Th. (eds.) Proceedings of the International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making IUKM’2018, Hanoi, Vietnam, March 13–15, 2018

3. Baral, C., Fuentes, O., Kreinovich, V.: Why deep neural networks: a possible theoretical explanation. In: Ceberio, M., Kreinovich, V. (eds.) Constraint Programming and Decision Making: Theory and Applications, pp. 1–6. Springer Verlag, Berlin (2018)

4. Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)

5. Farhan, A., Kosheleva, O., Kreinovich, V.: Why max and average poolings are optimal in convolutional neural networks. In: Proceedings of the Seventh International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making IUKM’2019, Nara, Japan, March 27–29 (2019)

Cited by 5 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. Why Rectified Linear Unit Is Efficient in Machine Learning: One More Explanation;Studies in Systems, Decision and Control;2024

2. Why, in Deep Learning, Non-smooth Activation Function Works Better Than Smooth Ones;Studies in Systems, Decision and Control;2023

3. Why Rectified Linear Neurons: Two Convexity-Related Explanations;Biomedical and Other Applications of Soft Computing;2022-11-23

4. Invariance Explains Empirical Success of Many Intelligent Techniques;2022 IEEE 11th International Conference on Intelligent Systems (IS);2022-10-12

5. Uncertainty: Ideas Behind Neural Networks Lead Us Beyond KL- Decomposition and Interval Fields;2021 IEEE Symposium Series on Computational Intelligence (SSCI);2021-12-05

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