University of Cambridge > > Microsoft Research Cambridge, public talks > Algorithmic Differentiation (AD) Beyond Back Propagation

Algorithmic Differentiation (AD) Beyond Back Propagation

Add to your list(s) Download to your calendar using vCal

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

Back propagation amounts to adjoint AD of neural networks. It is relatively simple to understand and implement. First- and higher-order AD of large-scale numerical simulation programs yields a number of challenges some of which will be discussed during this presentation. Topics to be commented on include the use of symbolic adjoints inside of algorithmic adjoints, the validation of derivative code using differential invariants, and parallel AD.

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

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity