Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Slugin, Dmitry"'
Quantized low-precision neural networks are very popular because they require less computational resources for inference and can provide high performance, which is vital for real-time and embedded recognition systems. However, their advantages are ap
Externí odkaz:
http://arxiv.org/abs/2009.06488
The paper proposes an approach to training a convolutional neural network using information on the level of distortion of input data. The learning process is modified with an additional layer, which is subsequently deleted, so the architecture of the
Externí odkaz:
http://arxiv.org/abs/1912.00664
Publikováno v:
Proceedings of SPIE; 4/14/2019, Vol. 11041, p1-8, 8p
Autor:
Osten, Wolfgang, Nikolaev, Dmitry P., Zhou, Jianhong, Janiszewski, Igor, Slugin, Dmitry, Andreeva, Elena
Publikováno v:
Proceedings of SPIE; January 2021, Vol. 11605 Issue: 1 p116051H-116051H-6, 1044466p
Autor:
Osten, Wolfgang, Nikolaev, Dmitry P., Janiszewski, Igor M., Arlazarov, Vladimir V., Slugin, Dmitry G.
Publikováno v:
Proceedings of SPIE; January 2020, Vol. 11433 Issue: 1 p114330W-114330W-8, 1028979p
Autor:
Osten, Wolfgang, Nikolaev, Dmitry P., Zhou, Jianhong, Janiszewski, Igor, Slugin, Dmitry, Andreeva, Elena
Publikováno v:
Proceedings of SPIE; 10/29/2020, Vol. 11605, p116051H-116051H-6, 1p
Autor:
Verikas, Antanas, Nikolaev, Dmitry P., Radeva, Petia, Zhou, Jianhong, Tropin, Daniil V., Nikolaev, Dmitry P., Slugin, Dmitry G.
Publikováno v:
Proceedings of SPIE; March 2019, Vol. 11041 Issue: 1 p1104105-1104105-8