Abstract | ||
---|---|---|
This letter presents a theory of scanning a signal with a sliding window, where the window's mapping function is built upon a convolutional neural network (CNN). When using a CNN as the sliding window, we show that the resultant feature maps are equivalent to the maps obtained by applying another CNN (called EQ-ScanNet) to the whole signal. The EQ-ScanNet can be established by reconfiguring the or... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/LSP.2018.2869106 | IEEE Signal Processing Letters |
Keywords | Field | DocType |
Convolution,Finite impulse response filters,Microsoft Windows,Kernel,Windows,Time-domain analysis,Convolutional neural networks | Kernel (linear algebra),Microsoft Windows,Sliding window protocol,Decimation,Pattern recognition,Convolutional neural network,Convolution,Equivalence (measure theory),Artificial intelligence,Finite impulse response,Mathematics | Journal |
Volume | Issue | ISSN |
25 | 10 | 1070-9908 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huei-Fang Yang | 1 | 276 | 13.70 |
Yen-ting Chen | 2 | 162 | 18.83 |
Cheng-Hao Tu | 3 | 1 | 1.70 |
Chu-Song Chen | 4 | 2071 | 128.23 |