Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Stochastic Pooling for Regularization of Deep Convolutional Neural
Matthew Zeiler, Rob Fergus
Jan 17, 2013 (modified: Jan 17, 2013)ICLR 2013 conference submissionreaders: everyone
Abstract:We introduce a simple and effective method for regularizing large convolutional neural networks. We replace the conventional deterministic pooling operations with a stochastic procedure, randomly picking the activation within each pooling region according to a multinomial distribution, given by the activities within the pooling region. The approach is hyper-parameter free and can be combined with other regularization approaches, such as dropout and data augmentation. We achieve state-of-the-art performance on four image datasets, relative to other approaches that do not utilize data augmentation.
Enter your feedback below and we'll get back to you as soon as possible.