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

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

Description

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. https://pycon.de

More details at the conference page: https://de.pycon.org/program/RAS8UK Twitter: https://twitter.com/pydataberlin Twitter: https://twitter.com/pyconde

Details

Improve this page