Mathematical models and optimization methods have played a longstanding, critical role in the design of signal processing and analysis systems. In the past decade, data-driven approaches - especially deep learning - have been widely adopted and have achieved state-of-the-art results in various signal and image processing applications; this, however, is at the cost of interpretability and explainability of the model and its decisions. Despite their unprecedented performance and wide adoption, black-box deep learning models come with major shortcomings: training such deep learning models requires a large amount of data and (ground truth) annotations and consumes a significant amount of computational and power resources. Moreover, the performance of deep learning models is sensitive to deviations between the training and the test set, for example due to the presence of (adversarial) noise. This special issue gathers contributions related to innovative designs of model-aware deep learning models, novel approaches to train such models, and advanced topics concerning the understanding of such models.
Chouzenoux, E, Deligiannis, N & Pizurica, A 2026, 'Advances in Model-based Deep Learning', Signal Processing, vol. 238, 110222. https://doi.org/10.1016/j.sigpro.2025.110222
Chouzenoux, E., Deligiannis, N., & Pizurica, A. (2026). Advances in Model-based Deep Learning. Signal Processing, 238, Article 110222. https://doi.org/10.1016/j.sigpro.2025.110222
@article{71035ed572df425688f1dfe54f8545fc,
title = "Advances in Model-based Deep Learning",
abstract = "Mathematical models and optimization methods have played a longstanding, critical role in the design of signal processing and analysis systems. In the past decade, data-driven approaches - especially deep learning - have been widely adopted and have achieved state-of-the-art results in various signal and image processing applications; this, however, is at the cost of interpretability and explainability of the model and its decisions. Despite their unprecedented performance and wide adoption, black-box deep learning models come with major shortcomings: training such deep learning models requires a large amount of data and (ground truth) annotations and consumes a significant amount of computational and power resources. Moreover, the performance of deep learning models is sensitive to deviations between the training and the test set, for example due to the presence of (adversarial) noise. This special issue gathers contributions related to innovative designs of model-aware deep learning models, novel approaches to train such models, and advanced topics concerning the understanding of such models.",
author = "Emilie Chouzenoux and Nikos Deligiannis and Aleksandra Pizurica",
year = "2026",
month = jan,
doi = "10.1016/j.sigpro.2025.110222",
language = "English",
volume = "238",
journal = "Signal Processing",
issn = "0165-1684",
publisher = "Elsevier",
}