SiMaN : Sign-to-Magnitude Network Binarization
Binary neural networks (BNNs) have attracted broad research interest due to their efficient storage and computational ability. Nevertheless, a significant challenge of BNNs lies in handling discrete constraints while ensuring bit entropy maximization, which typically makes their weight optimization...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 5 vom: 10. Mai, Seite 6277-6288
|
|---|
| 1. Verfasser: |
Lin, Mingbao
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Ji, Rongrong,
Xu, Zihan,
Zhang, Baochang,
Chao, Fei,
Lin, Chia-Wen,
Shao, Ling |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|