Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Francazi, Emanuele"'
Autor:
Chen, Cheng, Kyathanahally, Sreenath, Reyes, Marta, Merkli, Stefanie, Merz, Ewa, Francazi, Emanuele, Hoege, Marvin, Pomati, Francesco, Baity-Jesi, Marco
Modern plankton high-throughput monitoring relies on deep learning classifiers for species recognition in water ecosystems. Despite satisfactory nominal performances, a significant challenge arises from Dataset Shift, which causes performances to dro
Externí odkaz:
http://arxiv.org/abs/2401.14256
Publikováno v:
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13783-13839, 2024
Understanding and controlling biasing effects in neural networks is crucial for ensuring accurate and fair model performance. In the context of classification problems, we provide a theoretical analysis demonstrating that the structure of a deep neur
Externí odkaz:
http://arxiv.org/abs/2306.00809
Publikováno v:
International Conference on Machine Learning 2023, (PMLR) 10285-10322
Data imbalance is a common problem in machine learning that can have a critical effect on the performance of a model. Various solutions exist but their impact on the convergence of the learning dynamics is not understood. Here, we elucidate the signi
Externí odkaz:
http://arxiv.org/abs/2207.00391