Taming the sigmoid bottleneck: Provably argmaxable sparse multi-label classification

A Grivas, A Vergari, A Lopez - Proceedings of the AAAI Conference on …, 2024 - ojs.aaai.org
Sigmoid output layers are widely used in multi-label classification (MLC) tasks, in which
multiple labels can be assigned to any input. In many practical MLC tasks, the number of …

Practical perspectives on symplectic accelerated optimization

V Duruisseaux, M Leok - Optimization Methods and Software, 2023 - Taylor & Francis
Geometric numerical integration has recently been exploited to design symplectic
accelerated optimization algorithms by simulating the Bregman Lagrangian and Hamiltonian …

Topic Recognition Using TED-LIUM Release 3

J Yao - 2022 IEEE 10th Region 10 Humanitarian Technology …, 2022 - ieeexplore.ieee.org
The widespread of mobile digital cameras and phones facilitate creation of multimedia
including audio and video records. Categorizing the spoken documents by themes is a key …

[PDF][PDF] Discover What The Experts Really Say

CEF In, MHM van Esch - pure.tue.nl
This study explores a novel method to investigate expert commentary. Within the research
field of expertise, it is currently unknown how experts structure their speech. This thesis used …