Overfitting remedy by sparsifying regularization on fully-connected layers of CNNs
Sign Up to like & getrecommendations! Published in 2019 at "Neurocomputing"
DOI: 10.1016/j.neucom.2018.03.080
Abstract: Abstract Deep learning, especially Convolutional Neural Networks (CNNs), has been widely applied in many domains. The large number of parameters in a CNN allow it to learn complex features, however, they may tend to hinder… read more here.
Keywords: overfitting remedy; sparsifying regularization; connected layers; regularization ... See more keywords
High-fidelity imaging through a perturbed multimode fiber using a u-architecture network with fully connected layers.
Sign Up to like & getrecommendations! Published in 2024 at "Applied optics"
DOI: 10.1364/ao.542527
Abstract: The multimode fiber transmission is highly sensitive to perturbations, which imposes many limitations on its application in endoscopic imaging. Here, a u-architecture network with fully connected layers (FC-UANET) is designed to improve robustness to perturbations,… read more here.
Keywords: architecture network; multimode; connected layers; network fully ... See more keywords