Stability of self-organizing net fragments as inductive bias for next-generation deep learning
At a glance
- Project leader : Prof. Dr. Thilo Stadelmann
- Project team : Dr. Ricardo Chavarriaga, Dr. Oliver Dürr, Prof. Dr. Rudolf Marcel Füchslin, Prof. Dr. Benjamin Grewe, Prof. Dr. Christoph Heitz, Prof. Dr. Thomas Ott, Prof. Dr. Christoph von der Malsburg
- Project budget : CHF 189'504
- Project status : ongoing
- Funding partner : Public sector (excl. federal government) (Kanton Zürich / Digitalisierungsinitiative DIZH)
- Project partner : Universität Zürich / Neural Learning and Intelligent Systems Group, Universität Freiburg / Center Faith & Society
- Contact person : Thilo Stadelmann
Description
We recently released "A Theory of Natural Intelligence", proposing a possible key to the emergence of intelligence in biological learners. Goal of this fellowship is to develop a technical implementation of the concept of self-organizing netfragments within contemporary deep artificial neural nets.
Publications
-
Segessenman, Jan; Stadelmann, Thilo; Andrew, Davison; Oliver, Dürr,
2023.
Assessing deep learning : a work program for the humanities in the age of artificial intelligence.
SSRN.
Available from: https://doi.org/10.21256/zhaw-28651