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

  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

Algorithmic Differentiation (AD) Beyond Back Propagation

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.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

https://zoom.us/j/98085179345?pwd=cFRrTm9VNTk3QWlVdGNVMzg0N3Vldz09 LT2, Engineering, Department of Average on Saturdays: 7736.34751773 kWh

Other talks

Group Work Title to be confirmed Title tbc Title and abstract tba Title TBC Title and abstract tba
 

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