University of Cambridge > Talks.cam > Churchill CompSci Talks > Autoencoders

  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

Autoencoders

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.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

L1 Meeting Rooms, Hutchison/MRC Research Centre, Addenbrooke's Campus Quality Spares Centre Hybrid: in-person in Cambridge & online via Teams

Other talks

Market Failure, Organ Shortage, Pandemic and Climate Change: The Architecture of Cooperation Title to be confirmed Title to be confirmed Caribbean Trip and Cacti A Data-Centric Approach to AI Adaptation and Alignment Ensemble inequivalence for systems with long-range interactions
 

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