Results 21 to 30 of about 175,760 (266)
CoRR, 2016 Deep Neural Networks often require good regularizers to generalize well. Dropout is one such regularizer that is widely used among Deep Learning practitioners. Recent work has shown that Dropout can also be viewed as performing Approximate Bayesian Inference over the network parameters.
Suraj Srinivas, R. Venkatesh Babu
openaire +2 more sources
CoRR, 2017 Recurrent neural networks (RNNs) are important class of architectures among neural networks useful for language modeling and sequential prediction. However, optimizing RNNs is known to be harder compared to feed-forward neural networks. A number of techniques have been proposed in literature to address this problem.
Konrad Zolna +3 more
openaire +3 more sources
, 2017 Dropout is used as a practical tool to obtain uncertainty estimates in large vision models and reinforcement learning (RL) tasks. But to obtain well-calibrated uncertainty estimates, a grid-search over the dropout probabilities is necessary - a prohibitive operation with large models, and an impossible one with RL.
Gal, Y, Hron, J, Kendall, A
openaire +4 more sources
Proceedings of the AAAI Conference on Artificial Intelligence, 2019 Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes random drop of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes for intelligent dropout can lead to better generalization as compared to the traditional dropout.
Rohit Keshari +2 more
openaire +3 more sources
2017 IEEE International Conference on Computer Vision (ICCV), 2017 Dropout is a very effective way of regularizing neural networks. Stochastically "dropping out" units with a certain probability discourages over-specific co-adaptations of feature detectors, preventing overfitting and improving network generalization.
Pietro Morerio +4 more
openaire +2 more sources
IEEE Transactions on Neural Networks and Learning Systems, 2018 Accepted by ...
Xu Shen 0001 +4 more
openaire +3 more sources
Journal of Applied Science and Engineering, 2022 In classroom teaching, artificial intelligence technology can help automate student behavior analysis and enable teachers to master learning efficiently and intuitively provide data support for subsequent optimization of teaching design and ...
Zhaozhen Xuan
doaj +1 more source
The dropout learning algorithm [PDF]
Artificial Intelligence, 2014 Dropout is a recently introduced algorithm for training neural network by randomly dropping units during training to prevent their co-adaptation. A mathematical analysis of some of the static and dynamic properties of dropout is provided using Bernoulli gating variables, general enough to accommodate dropout on units or connections, and with variable ...
Pierre Baldi, Peter J. Sadowski
openaire +3 more sources
Frontiers in Nutrition, 2022 IntroductionThe aim of the present study was to assess the dropout rate at 2, 6, and 12 months after an inpatient multidisciplinary residential program (MRP) for the treatment of obesity.
Simone Perna +13 more
doaj +1 more source
Frontiers in Rehabilitation Sciences, 2022 BackgroundCardiac rehabilitation (CR) is a class 1A recommendation and an integrated part of standard treatment for patients with cardiac disease. In Denmark, CR adheres to European guidelines, it is group-based and partly conducted in primary health ...
Maiken Bay Ravn +6 more
doaj +1 more source