Showing 2021Show all
2 papers · 1 filter
eess.SP2021
Low-rank tensor recovery for Jacobian-based Volterra identification of parallel Wiener-Hammerstein systems
Konstantin Usevich, Philippe Dreesen, Mariya Ishteva
We consider the problem of identifying a parallel Wiener-Hammerstein structure from Volterra kernels. Methods based on Volterra kernels typically resort to coupled tensor decomposi…
cs.LG2021
Tensor-based framework for training flexible neural networks
Yassine Zniyed, Konstantin Usevich, Sebastian Miron +1
Activation functions (AFs) are an important part of the design of neural networks (NNs), and their choice plays a predominant role in the performance of a NN. In this work, we are…