S Amini, M Soltanian, M Sadeghi… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Deep learning architectures employ various regularization terms to handle different types of priors. Non-smooth regularization terms have shown promising performance in the deep …
We present a unitary approach to the design of incoherent frames and to dictionary learning, by using a single function that promotes incoherence for both problems. This function has a …
L Shi, G Qu - IEEE Access, 2024 - ieeexplore.ieee.org
In compressed sensing (CS), coherence is a simple and practical measure of the quality of a sensing matrix. The smaller the coherence of the sensing matrix, the better the …
M Sadeghi, P Magron - arXiv preprint arXiv:2203.15758, 2022 - arxiv.org
Structuring the latent space in probabilistic deep generative models, eg, variational autoencoders (VAEs), is important to yield more expressive models and interpretable …