Tensor Networks for Data Science: Stability, Efficiency and Explainability at Scale

Project funded by Novo Nordisk Foundation (Programmes and collaborations), grant NNF23OC0083524. Participating organisations named by the source: DTU Technical University of Denmark. Runs n/a to 2029-02-28. Keywords: Algorithm development, Artificial Intelligence/Machine Learning/Deep Learning, Big Data, Food Science, Quantum Technologies. Source: OpenAIRE Graph, from the funder's project data (collected by OpenAIRE on 2025-08-01); national funding data, not CORDIS; selected because its keywords name quantum. Abstract given by the source: Tensor networks represent exponentially large data structures in an efficient manner. This compressed representation can lead to dramatic improvements in storage and processing. Because of this, tensor networks have become a central tool in physics and quantum computation. While tensor networks are expected to play just as important a role in data science, their adoption has been hampered by some conceptual and technical obstacles. By combining insight from physics, data science, and chemometrics, this project will overcome these obstacles and establish tensor networks as the go-to tool for very large-scale data modelling. Furthermore, since tensor networks possess a clean mathematical structure, they typically provide explainable models – in contrast to modern deep learning. We will apply the new methods to key problems in machine learning, chemometrics and quantum computation_x000D_

Original source.

Source: OpenAIRE Graph: projects of national funders, OpenAIRE, from the project data of Novo Nordisk Foundation. Retrieved 2026-11-02. Licence: Creative Commons Attribution 4.0 (OpenAIRE Graph). Selected metadata, adapted presentation; the publisher's record is authoritative. No endorsement by the source is implied. Licence: Creative Commons Attribution 4.0 (CC BY 4.0).

AI-assisted summary: The project "Tensor Networks for Data Science" is funded by the Novo Nordisk Foundation and involves DTU Technical University of Denmark, running until February 28, 2029. It aims to enhance the use of tensor networks in data science by addressing existing challenges. Suggested technology pillar: computing. Generated by AI from the public source text; it may contain errors and the original source is authoritative.