2019
AAAI
AAAI 2019
Guided Dropout
Abstract
Abstract 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.
🚀
Conference Pioneer
— AAAI 2019
🌉
Interdisciplinary Bridge
— Deep Learning and Machine Learning
📈
Trend Setter
— Regularization
🧭
Keyword Pioneer
— guided dropout
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Security & Privacy, Speech & Audio
Authors
Topics
Machine Learning > Core Methods > Classification
Machine Learning > Optimization & Theory > Neural Network Optimization
Deep Learning > Techniques > Normalization
Deep Learning > Optimization & Theory > Neural Network Optimization
Deep Learning > Learning Types > Deep Learning
Deep Learning > Optimization & Theory > Model Compression
Machine Learning > Learning Types > Regularization
Deep Learning > Techniques > Regularization