University of Cambridge > Talks.cam > Microsoft Research Cambridge, public talks > Neural Ordinary Differential Equations

  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

Neural Ordinary Differential Equations

Download to your calendar using vCal

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins .

ī‚§ Please note, this event may be recorded. Microsoft will own the copyright of any recording and reserves the right to distribute it as required.

We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black-box differential equation solver. These continuous-depth models have constant memory cost, adapt their evaluation strategy to each input, and can explicitly trade numerical precision for speed. We demonstrate these properties in continuous-depth residual networks and continuous-time latent variable models. We also construct continuous normalizing flows, a generative model that can train by maximum likelihood, without partitioning or ordering the data dimensions. For training, we show how to scalably backpropagate through any ODE solver, without access to its internal operations. This allows end-to-end training of ODEs within larger models.

This talk is part of the Microsoft Research Cambridge, public talks series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

FW26, William Gates Building Room 117, Mary Allan Building, Homerton College, Hills Road, Cambridge CB2 8PQ Meeting Room 1, 17 Mill Lane, Cambridge

Other talks

Ensemble inequivalence for systems with long-range interactions The Inaccessible Game Title to be confirmed TBC The organisational management of traumatic stress Disentangling preventative & ejective AGN feedback on a population basis with simulations, observations & machine learning
 

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