Practical data efficient deep learning trough contrastive self-supervised learning
Auf einen Blick
- Projektleiter/in : Lukas Tuggener
- Projektvolumen : CHF 60'480
- Projektstatus : laufend
- Drittmittelgeber : Öffentliche Hand (ohne Bund)
- Projektpartner : Universität Zürich / Neural Learning and Intelligent Systems Group
- Kontaktperson : Lukas Tuggener
Beschreibung
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.