Deep neural networks on diffeomorphism groups for optimal shape reparametrization

Author:

Celledoni Elena,Glöckner Helge,Riseth Jørgen N.ORCID,Schmeding Alexander

Funder

Horizon 2020

Publisher

Springer Science and Business Media LLC

Subject

Applied Mathematics,Computational Mathematics,Computer Networks and Communications,Software

Reference39 articles.

1. Agrachev, A., Caponigro, M.: Controllability on the group of diffeomorphisms. Annales de l’Institut Henri Poincaré C, Analyse non linéaire 26(6), 2503–2509 (2009). https://doi.org/10.1016/j.anihpc.2009.07.003

2. Agrachev, A., Sarychev, A.: Control on the manifolds of mappings with a view to the deep learning. Journal of Dynamical and Control Systems (2021). https://doi.org/10.1007/s10883-021-09561-2

3. Bauer, M., Bruveris, M., Marsland, S., Michor, P.W.: Constructing reparameterization invariant metrics on spaces of plane curves. Differential Geometry and its Applications 34, 139–165 (2014). https://doi.org/10.1016/j.difgeo.2014.04.008

4. Behrmann, J., Grathwohl, W., Chen, R.T.Q., Duvenaud, D., Jacobsen, J.H.: Invertible residual networks. In: K. Chaudhuri, R. Salakhutdinov (eds.) Proceedings of the $$36^{{\rm th}}$$ International Conference on Machine Learning, Proceedings of Machine Learning Research, vol. 97, pp. 573–582. PMLR, Long Beach, California, USA (2019). URL https://proceedings.mlr.press/v97/behrmann19a.html

5. Behrmann, J., Vicol, P., Wang, K.C., Grosse, R., Jacobsen, J.H.: Understanding and mitigating exploding inverses in invertible neural networks. In: A. Banerjee, K. Fukumizu (eds.) Proceedings of The $$24^{{\rm th}}$$ International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research, vol. 130, pp. 1792–1800. PMLR, Virtual (2021). URL https://proceedings.mlr.press/v130/behrmann21a.html

Cited by 1 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. Designing stable neural networks using convex analysis and ODEs;Physica D: Nonlinear Phenomena;2024-07

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