Double backwards is PyTorch's way of implementing higher order differentiation. Why might you want it? How does it work? What are some of the weird things that happen when you do this?Further reading.<ul><li>Epic PR that added double backwards support for convolution initially <a href="https://github.com/pytorch/pytorch/pull/1643">https://github.com/pytorch/pytorch/pull/1643</a></li></ul>

Double backwards is PyTorch's way of implementing higher order differentiation. Why might you want it? How does it work? What are some of the weird things that happen when you do this? Further reading.Epic PR that added double backwards support for convolution initially https://github.com/pytorch/pytorch/pull/1643

Double backwards is PyTorch's way of implementing higher order differentiation. Why might you want it? How does it work? What are some of the weird things that happen when you do this?Further reading.<ul><li>Epic PR that added double backwards support for convolution initially <a href="https://github.com/pytorch/pytorch/pull/1643" rel="noopener noreferrer">https://github.com/pytorch/pytorch/pull/1643</a></li></ul>

Double backwards

The PyTorch Developer Podcast is a place for the PyTorch dev team to do bite sized (10-20 min) topics about all sorts of internal development topics in PyTorch.

Share Double backwards

Sign up to save your podcasts

Double backwards

Double backwards

More shows like PyTorch Developer Podcast

Talk Python To Me

Science Weekly

Cautionary Tales with Tim Harford

All-In with Chamath, Jason, Sacks & Friedberg