Quantized wavelet scattering networks for signal classification
2019
While convolutional neural networks (CNNs) are powerful tools in machine learning, their construction is far from a science. In addition, instantiations of CNNs are highly memory expensive and typically require large training sets. Wavelet scattering networks (WSNs) could provide a simple means of testing quantization schemes for CNNs, without the added complexity of adjustable parameters. Using the MSTAR database, the performance of a WSN in combination with several quantization schemes is examined.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
8
References
2
Citations
NaN
KQI