2 papers
eess.SP2018
Gradient-based Filter Design for the Dual-tree Wavelet Transform
Daniel Recoskie, Richard Mann
The wavelet transform has seen success when incorporated into neural network architectures, such as in wavelet scattering networks. More recently, it has been shown that the dual-t…
cs.LG2018
Learning Sparse Wavelet Representations
Daniel Recoskie, Richard Mann
In this work we propose a method for learning wavelet filters directly from data. We accomplish this by framing the discrete wavelet transform as a modified convolutional neural ne…