CORDIS Project
Funding breakdown and partner intelligence are Premium
Sign in and upgrade to Premium for EU contribution totals, consortium analytics, OpenAlex research context, and AI summaries. · 0 consortium intelligence fields visible of 1
Start free • Cancel anytime • 14-day refund guarantee
The CHALKS project investigates the architecture of Artificial Neural Networks using computational topology and sheaf theory. It aims to enhance explainability by analyzing data representations across hidden layers and understanding the evolution of topological complexity to inform architectural design.
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.
UNIVERSIDAD DE SEVILLA
Partner organizations (coordinator is shown above), with normalized type and CORDIS activity type. Guests see up to 4 partners.
NATIONAL UNIVERSITY CORPORATION THEUNIVERSITY OF TOKYO
Japan, Tokyo
Type: University / higher education
Activity type: Higher or Secondary Education Establishments
SME: No
Mathematical Institute, University of Oxford
United Kingdom, Oxford
Type: Company (for-profit)
Activity type: Private for-profit entities (excluding Higher or Secondary Education Establishments)
SME: No
Similar projects, consortium collaboration history, frequent partners, and OpenAlex research context.
Guests see up to 5 EuroSciVoc fields.
Guests see up to 5 topics.
Guests see up to 5 keywords.
