Abstract | ||
---|---|---|
We are witnessing an explosive development and widespread application of deep neural networks (DNNs) in various fields. However, DNN models, especially a convolutional neural network (CNN), usually involve massive parameters and are computationally expensive, making them extremely dependent on high-performance hardware. This prohibits their further extensions, e.g., applications on mobile devices.... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TNNLS.2017.2774288 | IEEE Transactions on Neural Networks and Learning Systems |
Keywords | Field | DocType |
Convolutional codes,Acceleration,Quantization (signal),Computational modeling,Mobile handsets,Training,Tensile stress | Convolutional code,Pattern recognition,Convolutional neural network,Inference,Computer science,Mobile device,Acceleration,Artificial intelligence,Contextual image classification,Computer engineering,Approximation error,Computation | Journal |
Volume | Issue | ISSN |
29 | 10 | 2162-237X |
Citations | PageRank | References |
17 | 0.70 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jian Cheng | 1 | 1327 | 115.72 |
Jiaxiang Wu | 2 | 66 | 4.99 |
Cong Leng | 3 | 241 | 13.20 |
Yuhang Wang | 4 | 204 | 14.84 |
qinghao hu | 5 | 163 | 8.86 |