Active Computing & AI Psychology & Behaviour

TopologiCal ApproacH to Artificial NeurAL NetworKS

Funder EC (part of European Union)
Consortium coordinator Not published Shown separately and not presented as the UK funding recipient.
UK recipients
Funding Not disclosed
Period Feb 2025 — Jan 2028

Summary

Original abstract (not yet simplified)

The project TopologiCal ApproacH to Artificial NeurAL NetworKS (CHALKS) will focus on the study of Artificial Neural Networks architecture based on computational topology approaches and sheaf theory. More specifically, towards Explainability, we plan to study the data representations through the different hidden layers of ANNs and track the topological complexity evolution. Then, we want to characterize the needed architecture based...

View original technical description
The project TopologiCal ApproacH to Artificial NeurAL NetworKS (CHALKS) will focus on the study of Artificial Neural Networks architecture based on computational topology approaches and sheaf theory. More specifically, towards Explainability, we plan to study the data representations through the different hidden layers of ANNs and track the topological complexity evolution. Then, we want to characterize the needed architecture based on the topological complexity.

Related Research

Grants with similar aims, by meaning.

Multilayer Algorithmics to Leverage Graph Structure (MultilayerALGS)
Topological Analysis of Neural Systems
Algebraic Topology based Machine Learning
Applications of category theory and topology to machine learning
Persistent topological structures in noisy images

Original classification

HORIZON

Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.