Dropout with Tabu Strategy for Regularizing Deep Neural Networks

• Published in: arXiv.org
• Main Authors: Ma, Zongjie, Sattar, Abdul, Zhou, Jun, Chen, Qingliang, Su, Kaile
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 29.08.2018
• Subjects: Neural networks; Performance enhancement; Propagation; Regularization

Dropout has proven to be an effective technique for regularization and preventing the co-adaptation of neurons in deep neural networks (DNN). It randomly drops units with a probability \(p\) during the training stage of DNN. Dropout also provides a way of approximately combining exponentially many d...