Results 11 to 20 of about 118,488 (274)
Information Plane Analysis for Dropout Neural Networks
CoRR, 2023 The information-theoretic framework promises to explain the predictive power of neural networks. In particular, the information plane analysis, which measures mutual information (MI) between input and representation as well as representation and output, should give rich insights into the training process.
Linara Adilova +2 more
openaire +3 more sources
MOOC Dropout Prediction Using FWTS-CNN Model Based on Fused Feature Weighting and Time Series
IEEE Access, 2020 High dropout rates have been a major problem affecting the development of Massive Open Online Courses (MOOCs). Student dropout prediction can help teachers identify students who are tending to fail and provide extra help in a timely manner, helping to ...
Yafeng Zheng +3 more
doaj +1 more source
Dropout Rademacher complexity of deep neural networks [PDF]
Science China Information Sciences, 2016 Great successes of deep neural networks have been witnessed in various real applications. Many algorithmic and implementation techniques have been developed, however, theoretical understanding of many aspects of deep neural networks is far from clear. A particular interesting issue is the usefulness of dropout, which was motivated from the intuition of
Wei Gao 0008, Zhi-Hua Zhou
openaire +2 more sources
Robustness of Sparsely Distributed Representations to Adversarial Attacks in Deep Neural Networks
Entropy, 2023 Deep learning models have achieved an impressive performance in a variety of tasks, but they often suffer from overfitting and are vulnerable to adversarial attacks.
Nida Sardar +3 more
doaj +1 more source
Regularization of deep neural networks with spectral dropout [PDF]
Neural Networks, 2019 The big breakthrough on the ImageNet challenge in 2012 was partially due to the `dropout' technique used to avoid overfitting. Here, we introduce a new approach called `Spectral Dropout' to improve the generalization ability of deep neural networks. We cast the proposed approach in the form of regular Convolutional Neural Network (CNN) weight layers ...
Salman H. Khan 0001 +2 more
openaire +3 more sources
R-Drop: Regularized Dropout for Neural Networks
CoRR, 2021 Accepted by NeurIPS ...
Xiaobo Liang +8 more
openaire +3 more sources
A primer on deep learning and convolutional neural networks for clinicians
Insights into Imaging, 2021 Deep learning is nowadays at the forefront of artificial intelligence. More precisely, the use of convolutional neural networks has drastically improved the learning capabilities of computer vision applications, being able to directly consider raw data ...
Lara Lloret Iglesias +7 more
doaj +1 more source
A CONCRETE DROPOUT NEURAL NETWORK FOR SHEAR SONIC LOG PREDICTION [PDF]
Romanian Journal of Petroleum & Gas TechnologyAssessing the risk associated with drilling and wellbore stability studies requires the shear sonic log. These logs apart from distinguishing formation fluid from lithology are needed to obtain geo-mechanical rock parameters required for the safe design ...
Ephraim Ojoajogu Enemali +3 more
doaj +1 more source
Less Is More: Adaptive Trainable Gradient Dropout for Deep Neural Networks
Sensors, 2023 The undeniable computational power of artificial neural networks has granted the scientific community the ability to exploit the available data in ways previously inconceivable.
Christos Avgerinos +2 more
doaj +1 more source
Selective Dropout for Deep Neural Networks [PDF]
, 2016 Dropout has been proven to be an effective method for reducing overfitting in deep artificial neural networks. We present 3 new alternative methods for performing dropout on a deep neural network which improves the effectiveness of the dropout method over the same training period.
Erik Barrow +2 more
openaire +1 more source