Stability of self-organizing net fragments as inductive bias for next-generation deep learning
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.
Key data
Projectlead
Project team
Prof. Dr. Rudolf Marcel Füchslin, Prof. Dr. Thomas Ott, Dr. Ricardo Chavarriaga, Prof. Dr. Christoph Heitz, Pascal Sager, Prof. Dr. Christoph von der Malsburg, Prof. Dr. Benjamin Grewe, Dr. Oliver Dürr
Project partners
Universität Zürich UZH / Neural Learning and Intelligent Systems Group; Universität Freiburg / Center Faith & Society
Project status
completed, 09/2023 - 08/2025
Institute/Centre
Centre for Artificial Intelligence (CAI); Institute of Computational Life Sciences (ICLS); Institute of Applied Mathematics and Physics (IAMP); Institute for Data Science (IDS)
Funding partner
Digitalisierungsinitiative der Zürcher Hochschulen DIZH
Project budget
189'504 CHF
Publications
-
A comprehensive survey of agents for computer use : foundations, challenges, and future directions
2026 Sager, Pascal J.; Meyer, Benjamin; Yan, Peng; von Wartburg-Kottler, Rebekka; Etaiwi, Layan; Enayati, Aref; Nobel, Gabriel; Abdulkadir, Ahmed; Grewe, Benjamin F.; Stadelmann, Thilo
-
The underlying structures of self-attention : symmetry, directionality, and emergent dynamics in Transformer training
2025 Saponati, Matteo; Sager, Pascal; Aceituno, Pau Vilimelis; Stadelmann, Thilo; Grewe, Benjamin
-
Assessing deep learning : a work program for the humanities in the age of artificial intelligence
2023 Segessenmann, Jan; Stadelmann, Thilo; Davison, Andrew; Dürr, Oliver
-
Assessing deep learning : a work program for the humanities in the age of artificial intelligence
2023 Segessenman, Jan; Stadelmann, Thilo; Andrew, Davison; Oliver, Dürr
