Lê, D. H., Luong, V. H., & Deligiannis, N. (2019). Designing recurrent neural networks by unfolding an L1-L1 minimization algorithm. In IEEE International Conference on Image Processing (pp. 2329-2333). IEEE. https://doi.org/10.1109/ICIP.2019.8803281

@inproceedings{79074000fc2849cda86ce6d153b9217a,
title = "Designing recurrent neural networks by unfolding an L1-L1 minimization algorithm",
abstract = "We propose a new deep recurrent neural network (RNN) architecture for sequential signal reconstruction. Our network is designed by unfolding the iterations of the proximal gradient method that solves the l1-l1 minimization problem. As such, our network leverages by design that signals have a sparse representation and that the difference between consecutive signal representations is also sparse. We evaluate the proposed model in the task of reconstructing video frames from compressive measurements and show that it outperforms several state-of-the-art RNN models.",
keywords = "Deep learning, Explainable AI, RNNs",
author = "L{\^e}, \{Duy Hung\} and Luong, \{Van Huynh\} and Nikolaos Deligiannis",
year = "2019",
month = sep,
doi = "10.1109/ICIP.2019.8803281",
language = "English",
isbn = "978-1-5386-6250-2",
pages = "2329--2333",
booktitle = "IEEE International Conference on Image Processing",
publisher = "IEEE",
note = "IEEE International Conference on Image Processing 2019, ICIP ; Conference date: 22-09-2019 Through 25-09-2019",
}