2018/12/10 by Rohit Keshari, Richa Singh, Keshari, Rohit +3
Computer Science · Mathematics · #Advanced Neural Network Applications #Anomaly Detection Techniques and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1812.03965
Accepted in AAAI2019
arxiv created 2018/12/10 · openalex publication_date 2018/12/10 · arxiv updated 2018/12/11 · openalex created_date 2024/04/11 · openalex updated_date 2026/07/28
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. 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.