Guided Dropout
Not on the map. Why?
Abstract (arXiv)
Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes textitrandom 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. In this research, we propose "guided dropout" for training deep neural network which drop nodes by measuring the strength of each node. We also demonstrate that conventional dropout is a specific case of the proposed guided dropout. Experimental evaluation on multiple datasets including MNIST, CIFAR10, CIFAR100, SVHN, and Tiny ImageNet demonstrate the efficacy of the proposed guided dropout.
Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Dec 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5; 2022: 4; 2023: 3; 2024: 2.
14 papers.
Sort:
By area:
- 2023Codebook Features: Sparse and Discrete Interpretability for Neural Networkscited by 48
- 2021Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Networkcited by 14
- 2023Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropoutscited by 5
- 2022Image Classification with Small Datasets: Overview and Benchmarkcited by 4
- 2021FocusedDropout for Convolutional Neural Networkcited by 3
- 2022Information Geometry of Dropout Trainingcited by 2
- 2024More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routingcited by 2
- 2021Exploring Dropout Discriminator for Domain Adaptationcited by 1
- 2021Feature Mining: A Novel Training Strategy for Convolutional Neural Networkcited by 1
- 2022Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reductioncited by 1
- 2023No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasetscited by 1
- 2021Deep Neural Networks Based Weight Approximation and Computation Reuse for 2-D Image Classificationcited by 0
2 more
- 2024More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing10 Oct 2024
- 2024Y-Drop: A Conductance based Dropout for fully connected layers11 Sep 2024
- 2023Codebook Features: Sparse and Discrete Interpretability for Neural Networks26 Oct 2023
- 2023No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasets4 Sep 2023
- 2023Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropouts9 Mar 2023
- 2022Image Classification with Small Datasets: Overview and Benchmark23 Dec 2022
- 2022Feature Weaken: Vicinal Data Augmentation for Classification20 Nov 2022
- 2022Information Geometry of Dropout Training22 Jun 2022
- 2022Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reduction2 Jun 2022
- 2021Feature Mining: A Novel Training Strategy for Convolutional Neural Network18 Jul 2021
- 2021Exploring Dropout Discriminator for Domain Adaptation9 Jul 2021
- 2021Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network3 Jul 2021
- 2023Codebook Features: Sparse and Discrete Interpretability for Neural Networkscited by 48
- 2023Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropoutscited by 5
- 2022Image Classification with Small Datasets: Overview and Benchmarkcited by 4
- 2021FocusedDropout for Convolutional Neural Networkcited by 3
- 2022Information Geometry of Dropout Trainingcited by 2
- 2021Exploring Dropout Discriminator for Domain Adaptationcited by 1
- 2021Feature Mining: A Novel Training Strategy for Convolutional Neural Networkcited by 1
- 2022Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reductioncited by 1
- 2023No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasetscited by 1
- 2021Deep Neural Networks Based Weight Approximation and Computation Reuse for 2-D Image Classificationcited by 0
- 2022Feature Weaken: Vicinal Data Augmentation for Classificationcited by 0
- 2024Y-Drop: A Conductance based Dropout for fully connected layerscited by 0
- 2024Y-Drop: A Conductance based Dropout for fully connected layers11 Sep 2024
- 2023Codebook Features: Sparse and Discrete Interpretability for Neural Networks26 Oct 2023
- 2023No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasets4 Sep 2023
- 2023Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropouts9 Mar 2023
- 2022Image Classification with Small Datasets: Overview and Benchmark23 Dec 2022
- 2022Feature Weaken: Vicinal Data Augmentation for Classification20 Nov 2022
- 2022Information Geometry of Dropout Training22 Jun 2022
- 2022Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reduction2 Jun 2022
- 2021Feature Mining: A Novel Training Strategy for Convolutional Neural Network18 Jul 2021
- 2021Exploring Dropout Discriminator for Domain Adaptation9 Jul 2021
- 2021Deep Neural Networks Based Weight Approximation and Computation Reuse for 2-D Image Classification28 Apr 2021
- 2021FocusedDropout for Convolutional Neural Network29 Mar 2021