Generalization Error Bounds for Deep Unfolding RNNs

Autor: Boris Joukovsky, Tanmoy Mukherjee, Van Huynh Luong, Nikolaos Deligiannis

Publikováno v: Vrije Universiteit Brussel

Recurrent Neural Networks (RNNs) are powerful models with the ability to model sequential data. However, they are often viewed as black-boxes and lack in interpretability. Deep unfolding methods take a step towards interpretability by designing deep

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::2ea24f41b23d8ca7dbf3fc2f72fe11d5
https://hdl.handle.net/20.500.14017/9838c212-1d80-47e0-ba1b-ba759e3b0014

DeepFPC: A deep unfolded network for sparse signal recovery from 1-Bit measurements with application to DOA estimation

Autor: Nikolaos Deligiannis, Peng Xiao, Bin Liao

Publikováno v: Signal Processing. 176:107699

In this paper, we introduce a novel deep neural network, coined DeepFPC, and investigate its application to tackling the problem of direction-of-arrival (DOA) estimation. DeepFPC is designed by unfolding the iterations of the fixed-point continuation

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e6d4ef35a08fb9d85c6e6ef82c627d75
https://doi.org/10.1016/j.sigpro.2020.107699

Exploring Side Information for DVB-t-based Passive Radars

Autor: Edison Cristofani, Osama Mahfoudia, Mathias Becquaert, Xavier Neyt, François Horlin, Nikolaos Deligiannis, Johan Stiens, Marijke Vandewal

Publikováno v: Vrije Universiteit Brussel

Passive radars based on DVB-t transmissions can benefit from the outstanding advantages that compressed sensing offers in terms of less acquired data, hence potentially reducing hardware requirements, and achieving reconstructed scene simplification.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::3b62f91439f6ad3389998b44c1e5c52d
https://biblio.vub.ac.be/vubir/exploring-side-information-for-dvbtbased-passive-radars(e857e1e9-106b-4b22-a80c-b4ca8face485).html

A review of urban air pollution monitoring and exposure assessment methods

Autor: Frank Pasveer, Nikolaos Deligiannis, Xingzhe Xie, Sidharta Gautama, Wilfried Philips, Ivana Semanjski, Raj Thilak Rajan, Evangelia Tsiligianni

Publikováno v: ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
ISPRS International Journal of Geo-Information; Volume 6; Issue 12; Pages: 389
ISPRS International Journal of Geo-Information, Vol 6, Iss 12, p 389 (2017)

The impact of urban air pollution on the environments and human health has drawn increasing concerns from researchers, policymakers and citizens. To reduce the negative health impact, it is of great importance to measure the air pollution at high spa

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0891a6e995a71f1e28f625816761f059
https://biblio.ugent.be/publication/8540155/file/8540158

Reference-based compressed sensing: A sample complexity approach

Autor: João Mota, Lior Weizman, Nikolaos Deligiannis, Yonina Eldar, Miguel Rodrigues

Publikováno v: Vrije Universiteit Brussel

We address the problem of reference-based compressed sensing: reconstruct a sparse signal from few linear measurements using as prior information a reference signal, a signal similar to the signal we want to reconstruct. Access to reference signals a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::80540b183cbcb36ad9e8544ee10a49b9
https://hdl.handle.net/20.500.14017/0faf8401-6b1b-479c-8cd9-84f45ed854d8