Results 251 to 260 of about 118,488 (274)

Dropout effect on probabilistic neural network

2017 International Conference on Electrical, Computer and Communication Engineering (ECCE), 2017
To ignore noisy, skewed, correlated, imbalanced and unnecessary features from real life problems, the feature subset selection with learning algorithm was faced some problems of selecting these relevant features. Several factors like-skewed, high kurtosis valued, dependence or correlation influenced features as well as the classifiers performance.
Nazmul Shahadat, Bushra Rahman, Faisal Ahmed, Ferdows Anwar   +3 more
openaire   +1 more source

Corrdrop: Correlation Based Dropout for Convolutional Neural Networks

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
Convolutional neural networks (CNNs) can be easily over-fitted when they are over-parametered. The popular dropout that drops feature units randomly can’t always work well for CNNs, due to the problem of under-dropping. To eliminate this problem, some structural dropout methods such as SpatialDropout, Cutout and DropBlock have been proposed.
Yuyuan Zeng, Tao Dai 0001, Shu-Tao Xia
openaire   +1 more source

Analysis on the Dropout Effect in Convolutional Neural Networks

2017
Regularizing neural networks is an important task to reduce overfitting. Dropout [1] has been a widely-used regularization trick for neural networks. In convolutional neural networks (CNNs), dropout is usually applied to the fully connected layers.
Sungheon Park, Nojun Kwak
openaire   +1 more source

Biased Dropout and Crossmap Dropout: Learning towards effective Dropout regularization in convolutional neural network

Neural Networks, 2018
Training a deep neural network with a large number of parameters often leads to overfitting problem. Recently, Dropout has been introduced as a simple, yet effective regularization approach to combat overfitting in such models. Although Dropout has shown remarkable results on many deep neural network cases, its actual effect on CNN has not been ...
Alvin Poernomo, Dae-Ki Kang
openaire   +2 more sources

Controlled dropout: A different dropout for improving training speed on deep neural network

2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2017
Dropout is a technique widely used for preventing overfitting while training deep neural networks. However, applying dropout to a neural network typically increases the training time. This paper proposes a different dropout approach called controlled dropout that improves training speed by dropping units in a column-wise or row-wise manner on the ...
ByungSoo Ko, Han-Gyu Kim, Ho-Jin Choi
openaire   +1 more source

Understanding Dropout for Graph Neural Networks

Companion Proceedings of the Web Conference 2022, 2022
Juan Shu, Bowei Xi, Yu Li 0006, Fan Wu, Charles A. Kamhoua, Jianzhu Ma   +5 more
openaire   +1 more source

Soft Dropout Method in Training of Contextual Neural Networks

2020
Various regularization techniques were developed to prevent many adverse effects that may appear during the training of contextual and non-contextual neural networks. The problems include e.g.: overfitting, vanishing of the gradient and too high increase in weight values. A commonly used solution that limits many of those is the dropout.
Krzysztof Wolk, Rafal Palak, Erik Dawid Burnell   +2 more
openaire   +1 more source

On the Use of Dropouts in Neural Networks for System Identification and Control

2018 IEEE Symposium Series on Computational Intelligence (SSCI), 2018
As universal function approximators, neural networks have been successfully used for nonlinear dynamical system identification and control. Recent developments in neural network regularisation methods include dropouts. Here, the outputs of hidden units are dropped randomly with a probability which is tuned as a hyperparameter.
Shrikanth M. Yadav, Koshy George
openaire   +2 more sources

Forward propagation dropout in deep neural networks using Jensen–Shannon and random forest feature importance ranking

Neural Networks, 2023
Mohammad Moattar
exaly  

Synchronous Dropout for Convolutional Neural Network

2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI), 2021
Ikkei Sakurai, Chihiro Ikuta
openaire   +1 more source