paper-with-me

홈 › Papers

Dither is Better than Dropout for Regularising Deep Neural Networks

2015-08-19 · Andrew J. R. Simpson

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.

📄 PDF Abstract BibTeX arXiv:1508.04826

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Parallel Dither and Dropout for Regularising Deep Neural Networks

2015-08-28 · Andrew J. R. Simpson

Effective regularisation during training can mean the difference between success and failure for deep neural networks. Recently, dither has been suggested as alternative to dropout for regularisation during batch-average…

Regularising Deep Networks with Deep Generative Models

2019-09-25 · Matthew Willetts, Alexander Camuto, Stephen Roberts, Chris Holmes

We develop a new method for regularising neural networks. We learn a probability distribution over the activations of all layers of the model and then insert imputed values into the network during training. We obtain a p…

Data AugmentationImputation

GIFnets: Differentiable GIF Encoding Framework

2020-06-24 · CVPR 2020 6 · Innfarn Yoo, Xiyang Luo, Yilin Wang, Feng Yang 외

Graphics Interchange Format (GIF) is a widely used image file format. Due to the limited number of palette colors, GIF encoding often introduces color banding artifacts. Traditionally, dithering is applied to reduce colo…

Quantity over Quality: Dithered Quantization for Compressive Radar Systems

2018-11-28

In this paper, we investigate a trade-off between the number of radar observations (or measurements) and their resolution in the context of radar range estimation. To this end, we introduce a novel estimation scheme that…

Compressive SensingQuantization

Distortion-Controlled Dithering with Reduced Recompression Rate

2024-02-26 · Morriel Kasher, Michael Tinston, Predrag Spasojevic

Dithering is a technique that can improve human perception of low-resolution data by reducing quantization artifacts. In this work we formalize and analytically justify two metrics for quantization artifact prominence, u…

Data CompressionImage CompressionQuantization