Practical data efficient deep learning trough contrastive self-supervised learning
At a glance
- Project leader : Lukas Tuggener
- Project budget : CHF 60'480
- Project status : completed
- Funding partner : Public sector (excl. federal government)
- Project partner : Universität Zürich / Neural Learning and Intelligent Systems Group
- Contact person : Lukas Tuggener
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.
Publications
-
Tuggener, Lukas; Sager, Pascal; Taoudi-Benchekroun, Yassine; Grewe, Benjamin F.; Stadelmann, Thilo,
2024.
So you want your private LLM at home? : a survey and benchmark of methods for efficient GPTs [paper].
In:
11th IEEE Swiss Conference on Data Science (SDS), Zurich, Switzerland, 30-31 May 2024.
ZHAW Zürcher Hochschule für Angewandte Wissenschaften.
Available from: https://doi.org/10.21256/zhaw-30279