Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Hinns, James"'
Autor:
Hinns, James, Martens, David
The rise of deep learning in image classification has brought unprecedented accuracy but also highlighted a key issue: the use of 'shortcuts' by models. Such shortcuts are easy-to-learn patterns from the training data that fail to generalise to new d
Externí odkaz:
http://arxiv.org/abs/2405.15661
In many AI applications today, the predominance of black-box machine learning models, due to their typically higher accuracy, amplifies the need for Explainable AI (XAI). Existing XAI approaches, such as the widely used SHAP values or counterfactual
Externí odkaz:
http://arxiv.org/abs/2309.17057