Dither is Better than Dropout for Regularising Deep Neural Networks

Abstract

Regularisation of deep neural networks (DNN) during training is critical to performance. By far the most popular method is known as dropout. Here, cast through the prism of signal processing theory, we compare and contrast the regularisation effects of dropout with those of dither. We illustrate some serious inherent limitations of dropout and demonstrate that dither provides a more effective regulariser.

References in corpus (3)

• Improving neural networks by preventing co-adaptation of feature detectors
• Over-Sampling in a Deep Neural Network
• Abstract Learning via Demodulation in a Deep Neural Network

Cited by in corpus (1)

• "Oddball SGD": Novelty Driven Stochastic Gradient Descent for Training Deep Neural Networks