The role of mutual information in variational classifiers

Author:

Vera MatiasORCID,Rey Vega Leonardo,Piantanida Pablo

Funder

H2020 Marie Skłodowska-Curie Actions

Universidad de Buenos Aires

Consejo Nacional de Investigaciones Científicas y Técnicas

Publisher

Springer Science and Business Media LLC

Subject

Artificial Intelligence,Software

Reference47 articles.

1. Achille, A., & Soatto, S. (2018a). Emergence of invariance and disentangling in deep representations. Journal of Machine Learning Research (JMLR), 19, 1–34.

2. Achille, A., & Soatto, S. (2018b). Information dropout: Learning optimal representations through noisy computation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(12), 2897–2905.

3. Alemi, A. A., Fischer, I., Dillon, J. V., & Murphy, K. (2016). Deep variational information bottleneck. CoRR arxiv:1612.00410.

4. Amjad, R. A., & Geiger, B. C. (2018). Learning representations for neural network-based classification using the information bottleneck principle. CoRR arxiv:1802.09766.

5. Bassily, R., Moran, S., Nachum, I., Shafer, J., & Yehudayoff, A. (2018). Learners that use little information. In Proceedings of machine learning research, PMLR, (Vol. 83, pp. 25–55).

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