Výsledky vyhledávání

The performance of medical research can be viewed and evaluated not only from the perspective of publication output, but also from the perspective of economic exploitability. Patents can represent the exploitation of research results and thus the tra

Externí odkaz: http://arxiv.org/abs/2412.00978

Zobrazit plný text záznamu

Report

Token Cropr: Faster ViTs for Quite a Few Tasks

Autor: Bergner, Benjamin, Lippert, Christoph, Mahendran, Aravindh

The adoption of Vision Transformers (ViTs) in resource-constrained applications necessitates improvements in inference throughput. To this end several token pruning and merging approaches have been proposed that improve efficiency by successively red

Externí odkaz: http://arxiv.org/abs/2412.00965

Zobrazit plný text záznamu

Report

Conformalised Conditional Normalising Flows for Joint Prediction Regions in time series

Autor: English, Eshant, Lippert, Christoph

Conformal Prediction offers a powerful framework for quantifying uncertainty in machine learning models, enabling the construction of prediction sets with finite-sample validity guarantees. While easily adaptable to non-probabilistic models, applying

Externí odkaz: http://arxiv.org/abs/2411.17042

Zobrazit plný text záznamu

Report

Scalable General Error Mitigation for Quantum Circuits

Autor: Döbler, Philip, Pflieger, Jannik, Jin, Fengping, De Raedt, Hans, Michielsen, Kristel, Lippert, Thomas, Jattana, Manpreet Singh

In quantum computing, error mitigation is a method to improve the results of an error-prone quantum processor by post-processing them on a classical computer. In this work, we improve the General Error Mitigation (GEM) method for scalability. GEM rel

Externí odkaz: http://arxiv.org/abs/2411.07916

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání