University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Deep learning as optimal control problems and Riemannian discrete gradient descent.

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Deep learning as optimal control problems and Riemannian discrete gradient descent.

Download to your calendar using vCal

  • UserElena Celledoni (Norwegian University of Science and Technology; Norwegian University of Science and Technology)
  • ClockThursday 21 November 2019, 15:05-15:45
  • HouseSeminar Room 2, Newton Institute.

If you have a question about this talk, please contact INI IT .

GCS - Geometry, compatibility and structure preservation in computational differential equations

We consider recent work where deep learning neural networks have been interpreted as discretisations of an optimal control problem subject to an ordinary differential equation constraint. We review the first order conditions for optimality, and the conditions ensuring optimality after discretisation. This leads to a class of algorithms for solving the discrete optimal control problem which guarantee that the corresponding discrete necessary conditions for optimality are fulfilled. The differential equation setting lends itself to learning additional parameters such as the time discretisation. We explore this extension alongside natural constraints (e.g. time steps lie in a simplex). We compare these deep learning algorithms numerically in terms of induced flow and generalisation ability.   References   - M Benning, E Celledoni, MJ Ehrhardt, B Owren, CB Schönlieb, Deep learning as optimal control problems: models and numerical methods, JCD.




This talk is part of the Isaac Newton Institute Seminar Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

MRC Laboratory Of Molecular Biology (LMB) Cripps Meeting Room 4, Cripps Court Building, Chesterton Road, Magdalene College Dept. of Engineering Trumpington Street, Baker Building - Oatley 1 Meeting Room

Other talks

Title to be confirmed Bacterial Physiology During Growth Arrest: Can It Be Targeted by Anti-Bacterial Therapeutics? Favourite Plants: the common, the captivating, and the curious Quantifying the unquantifiable? Assessing the importance of almsgiving in early modern France and Spain Title to be confirmed Fairy Tales
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity