Quantum Gradient Class Activation Map for Model Interpretability
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914909637312512 |
|---|---|
| author | Lin, Hsin-Yi Tseng, Huan-Hsin Chen, Samuel Yen-Chi Yoo, Shinjae |
| author_facet | Lin, Hsin-Yi Tseng, Huan-Hsin Chen, Samuel Yen-Chi Yoo, Shinjae |
| contents | Quantum machine learning (QML) has recently made significant advancements in various topics. Despite the successes, the safety and interpretability of QML applications have not been thoroughly investigated. This work proposes using Variational Quantum Circuits (VQCs) for activation mapping to enhance model transparency, introducing the Quantum Gradient Class Activation Map (QGrad-CAM). This hybrid quantum-classical computing framework leverages both quantum and classical strengths and gives access to the derivation of an explicit formula of feature map importance. Experimental results demonstrate significant, fine-grained, class-discriminative visual explanations generated across both image and speech datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_05899 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Quantum Gradient Class Activation Map for Model Interpretability Lin, Hsin-Yi Tseng, Huan-Hsin Chen, Samuel Yen-Chi Yoo, Shinjae Quantum Physics Artificial Intelligence Machine Learning Quantum machine learning (QML) has recently made significant advancements in various topics. Despite the successes, the safety and interpretability of QML applications have not been thoroughly investigated. This work proposes using Variational Quantum Circuits (VQCs) for activation mapping to enhance model transparency, introducing the Quantum Gradient Class Activation Map (QGrad-CAM). This hybrid quantum-classical computing framework leverages both quantum and classical strengths and gives access to the derivation of an explicit formula of feature map importance. Experimental results demonstrate significant, fine-grained, class-discriminative visual explanations generated across both image and speech datasets. |
| title | Quantum Gradient Class Activation Map for Model Interpretability |
| topic | Quantum Physics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2408.05899 |