Sony CSL

Emmanuel Deruty, Quentin Fresnel

FFT and Wavelets as input of neural networks.

Possible issues with FFT: • Choice of network architecture? • 1D input data (1 input vector = 1 window) or 2D input data (1 input vector = several reshaped windows)? • Recurrent or non-recurrent network? Non-recurrent possible in 2D case. • In case of 2D input data, is reshaping important? (eg. consequences in case of convolutional network) Possible issues with CWT: • Due to high dimensionality of CWT, is it feasible to set it as input of NN? • If it’s feasible, what reshaping? • Can we imagine a recurrent NN architecture with different time-scales [Alpay 2016] to suit CWT input?