Zobrazeno 1 - 10
of 144
pro vyhledávání: '"JinMei Lai"'
Publikováno v:
Integration. 87:231-240
Publikováno v:
IEEE Transactions on Circuits and Systems II: Express Briefs. 69:1637-1641
The binarized neural network (BNN) inference accelerators show great promise in cost-and power-restricted domains. However, the performances of these accelerators are still severely limited by the significant redundancies in BNNs inference. In this b
Publikováno v:
IEEE Geoscience and Remote Sensing Letters. 19:1-5
Publikováno v:
IEICE Transactions on Information and Systems. :1724-1733
Publikováno v:
2022 IEEE 16th International Conference on Solid-State & Integrated Circuit Technology (ICSICT).
Publikováno v:
IEICE Transactions on Information and Systems. :1367-1377
Publikováno v:
Proceedings of the Great Lakes Symposium on VLSI 2022.
Autor:
Qingliang Liu, Jinmei Lai
Publikováno v:
AAAI
Training deep neural networks is inherently subject to the predefined and fixed loss functions during optimizing. To improve learning efficiency, we develop Stochastic Loss Function (SLF) to dynamically and automatically generating appropriate gradie
Publikováno v:
Evidence-based complementary and alternative medicine : eCAM. 2022
This research was to analyze the effect of flavored Tongxie Yaofang on diarrheal irritable bowel syndrome (IBS) by the situation of intestinal microecology. The treatment mechanism was analyzed, so as to provide a more effective treatment method for
Publikováno v:
Electronics; Volume 12; Issue 1; Pages: 192
The programmability of FPGA suits the constantly changing convolutional neural network (CNN). However, several challenges arise when the previous FPGA-based accelerators update CNN. Firstly, although the model of RepVGG can balance accuracy and speed