Improving Differentiable Architecture Search via self-distillation.

Zhu, Xunyu; Li, Jian; Liu, Yong; Wang, Weiping

Zhu, Xunyu; Li, Jian; Liu, Yong; Wang, Weiping.

Afiliación

Zhu X; Institute of Information Engineering, Chinese Academy of Sciences, China; School of Cyber Security, University of Chinese Academy of Sciences, China. Electronic address: zhuxunyu@iie.ac.cn.
Li J; Institute of Information Engineering, Chinese Academy of Sciences, China; School of Cyber Security, University of Chinese Academy of Sciences, China. Electronic address: lijian9026@iie.ac.cn.
Liu Y; Gaoling School of Artificial Intelligence, Renmin University of China, China. Electronic address: liuyonggsai@ruc.edu.cn.
Wang W; Institute of Information Engineering, Chinese Academy of Sciences, China; School of Cyber Security, University of Chinese Academy of Sciences, China. Electronic address: wangweiping@iie.ac.cn.

Neural Netw ; 167: 656-667, 2023 Oct.

Article en En | MEDLINE | ID: mdl-37717323

Asunto(s)

Destilación; Conocimiento; Probabilidad

Palabras clave

Flatness; Knowledge distillation; Neural architecture search; Neural networks; Sharpness-aware minimization

Texto completo

Añadir a Mi BVS

Imprimir

XML

PubMed Links

Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Destilación / Conocimiento Idioma: En Revista: Neural Netw Asunto de la revista: NEUROLOGIA Año: 2023 Tipo del documento: Article Pais de publicación: Estados Unidos

Texto completo

Añadir a Mi BVS

Imprimir

XML

PubMed Links

Buscar en Google