Signal Denoising Using a New Class of Robust Neural Networks - Archive ouverte HAL Access content directly
Conference Papers Year :

Signal Denoising Using a New Class of Robust Neural Networks

(1) , (1) , (1) , (2)
1
2

Abstract

In this work, we propose a novel neural network architecture, called Adaptive Convolutional Neural Network (ACNN), which can be viewed as an intermediate solution between a standard convolutional network and a fully connected one. A constrained training strategy is developed to learn the parameters of such a network. The proposed algorithm allows us to control the Lipschitz constant of our ACNN to secure its robustness to adversarial noise. The resulting learning approach is evaluated for signal denoising based on a database of music recordings. Both qualitative and quantitative results show that the designed network is successful in removing Gaussian noise with unknown variance
Not file

Dates and versions

hal-03115064 , version 1 (19-01-2021)

Identifiers

Cite

Ana Neacsu, Kavya Gupta, Jean-Christophe Pesquet, Corneliu Burileanu. Signal Denoising Using a New Class of Robust Neural Networks. EUSIPCO 2020 - 28th European Signal Processing Conference, Jan 2021, Amsterdam, Netherlands. pp.1492-1496, ⟨10.23919/Eusipco47968.2020.9287630⟩. ⟨hal-03115064⟩
135 View
3 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More