Enhancing Neural Network Interpretability Through Deep Prior-Guided Expected Gradients

The increasing adoption of DNNs in critical domains such as healthcare, finance, and autonomous systems underscores the growing importance of explainable artificial intelligence (XAI). In these high-stakes applications, understanding the decision-making processes of models is essential for ensuring...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Su-Ying Guo, Xiu-Jun Gong
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	MDPI AG 2025-06-01
Saila:	Applied Sciences
Gaiak:	explainable AI expected gradients prior baseline feature attributions
Sarrera elektronikoa:	https://www.mdpi.com/2076-3417/15/13/7090
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!