2022 · 19 citations · 11 references
ComputingComputer ScienceArtificial IntelligenceComputer VisionMachine LearningDeep LearningLoss ReductionNeural NetworksOverfittingRepresentation LearningUnderfittingConvolutional Neural NetworksDropoutDropout ModelingElastic NetL1 RegularizationL2 RegularizationRegularizationRegularization Techniques
Deep learning techniques face the problem of overfitting due to their complex layer structure. Regularization methods are used to overcome this problem and improve the designed models. In this article, we use the combination of L1 regularization, L2 regularization, Elastic Net-regularization, and Dropout methods. The designed deep model using combination of these methods is considered with different rates. The deep network model using a combination of these methods is designed with different rates. Finally, the performance of all combination methods is compared with the Convolutional Neural Network model which does not use regularization methods. Experiments are performed using the Gold price per ounce data set and linear simulation model. The obtained results show that the performance of the combination model of Dropout and Elastic Net regularization is better than the other models.
11
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Group sparse regularization for deep neural networks
Simone Scardapane, Danilo Comminiello, Amir Hussain et al. · Neurocomputing · 2017 · 475 citations · Full text
Rotating your face using multi-task deep neural network
Junho Yim, Heechul Jung, ByungIn Yoo et al. · 2015 · 301 citations