Results 41 to 50 of about 118,488 (274)

Survey of Dropout Methods for Deep Neural Networks

CoRR, 2019
Dropout methods are a family of stochastic techniques used in neural network training or inference that have generated significant research interest and are widely used in practice. They have been successfully applied in neural network regularization, model compression, and in measuring the uncertainty of neural network outputs.
Alex Labach, Hojjat Salehinejad, Shahrokh Valaee   +2 more
openaire   +2 more sources

Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets

Applied Computer Systems, 2017
A technique of DropOut for preventing overfitting of convolutional neural networks for image classification is considered in the paper. The goal is to find a rule of rationally allocating DropOut layers of 0.5 rate to maximise performance. To achieve the
Romanuke Vadim V.
doaj   +1 more source

Maximum Relevance Minimum Redundancy Dropout with Informative Kernel Determinantal Point Process

Sensors, 2021
In recent years, deep neural networks have shown significant progress in computer vision due to their large generalization capacity; however, the overfitting problem ubiquitously threatens the learning process of these highly nonlinear architectures ...
Mohsen Saffari, Mahdi Khodayar, Mohammad Saeed Ebrahimi Saadabadi, Ana F. Sequeira, Jaime S. Cardoso   +4 more
doaj   +1 more source

Data Dropout in Arbitrary Basis for Deep Network Regularization

, 2017
An important problem in training deep networks with high capacity is to ensure that the trained network works well when presented with new inputs outside the training dataset.
Atia, George, Rahmani, Mostafa
core   +1 more source

Uncertainty propagation for dropout-based Bayesian neural networks

Neural Networks, 2021
Uncertainty evaluation is a core technique when deep neural networks (DNNs) are used in real-world problems. In practical applications, we often encounter unexpected samples that have not seen in the training process. Not only achieving the high-prediction accuracy but also detecting uncertain data is significant for safety-critical systems.
Yuki Mae, Wataru Kumagai, Takafumi Kanamori   +2 more
openaire   +2 more sources

Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays

IEEE Access, 2021
Automatic detection of solar array faults reduces maintenance costs and increases efficiency. In this paper, we address the problem of fault detection, localization, and classification in utility-scale photovoltaic (PV) arrays using machine learning ...
Sunil Rao, Gowtham Muniraju, Cihan Tepedelenlioglu, Devarajan Srinivasan, Govindasamy Tamizhmani, Andreas Spanias   +5 more
doaj   +1 more source

Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks

, 2018
Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as any target labels.
Chin, Peter, Kaeli, David, Lin, Xue, Wang, Siyue, Wang, Xiao, Wen, Wujie, Zhao, Pu   +6 more
core   +1 more source

A Comparative Study on Regularization Strategies for Embedding-based Neural Networks

, 2015
This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP. We chose two widely studied neural models and tasks as our testbed. We tried several frequently
Chen, Yunchuan, Jin, Zhi, Li, Ge, Lu, Yangyang, Mou, Lili, Peng, Hao   +5 more
core   +1 more source

Prediction of Surface Topography Parameters in Direct Laser Interference Patterning of Stainless Steel Using Infrared Monitoring and Convolutional Neural Networks

Advanced Engineering Materials, EarlyView.
This study presents an infrared monitoring approach for direct laser interference patterning (DLIP) combined with a convolutional neural network (CNN). Thermal emission data captured during structuring are used to predict surface topography parameters.
Lukas Olawsky, Marcelo Sallese, Leander Kläber, Clemens Kuhn, Keming Du, Andrés Fabián Lasagni   +5 more
wiley   +1 more source

Flipover outperforms dropout in deep learning

Visual Computing for Industry, Biomedicine, and Art
Flipover, an enhanced dropout technique, is introduced to improve the robustness of artificial neural networks. In contrast to dropout, which involves randomly removing certain neurons and their connections, flipover randomly selects neurons and reverts ...
Yuxuan Liang, Chuang Niu, Pingkun Yan, Ge Wang   +3 more
doaj   +1 more source