Contribute Media
A thank you to everyone who makes this possible: Read More

Equivariance in CNNs: how generalising the weight-sharing...


Speaker: Marysia Winkels

Track:PyData In this talk, we will explore how the weight-sharing property of the convolutional layer can be generalised to achieve equivariance towards transformations beyond just translation, how to implement this, and the results on real-world data.

Recorded at the PyConDE & PyData Berlin 2019 conference.

More details at the conference page: Twitter: Twitter:


Improve this page