University of Cambridge > > Churchill CompSci Talks > Autoencoders


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

If you have a question about this talk, please contact Matthew Ireland.

Autoencoders are a simple machine learning architecture trained only to reconstruct their original input. However, they’ve been applied to fields as diverse as dimensionality reduction, anomaly detection and data generation. In this talk I will explain how to develop this basic architecture into more advanced models capable of solving a wide range of unsupervised problems.

This talk is part of the Churchill CompSci 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