Practical data efficient deep learning trough contrastive self-supervised learning
Description
Deep Learning is the key building block of most modern AI systems, but its data hunger is a problem - especially from an applied perspective. The goal of this project is to enable data efficient practical deep learning by developing novel contrastive learning methods.
Key Data
Projectlead
Project partners
Universität Zürich / Neural Learning and Intelligent Systems Group
Project status
completed, 09/2022 - 09/2023
Funding partner
Public sector (excl. federal government)
Project budget
60'480 CHF
