Rethinking Feature Attribution for Neural Network Explanation

MCML Authors

Ashkan Khakzar

Dr.

* Former Member

→ Group Daniel Rückert
 Artificial Intelligence in Healthcare and Medicine

Abstract

Feature attribution is arguably the predominant approach for illuminating black-box neural networks. This dissertation rethinks feature attribution by leveraging critical neural pathways, identifying input features with predictive information, and evaluating feature attribution using the neural network model. The dissertation also rethinks feature attribution for the explanation of medical imaging models.

phdthesis Kha23

---

Dissertation

TU München. Aug. 2023

---

Authors

A. Khakzar

---

Links

URL

---

Research Area

 C1 | Medicine