Autoencoders have emerged as a useful framework for unsupervised learning of internal representations, and a wide variety of apparently conceptually disparate regularization techniques have been proposed to generate useful features. Here we extend existing denoising autoencoders to additionally inject noise before the nonlinearity, and at the hidden unit activations. We show that a wide variety of previous methods, including denoising, contractive, and sparse autoencoders, as well as dropout can be interpreted using this framework. This noise injection framework reaps practical benefits by providing a unified strategy to develop new internal representations by designing the nature of the injected noise. We show that noisy autoencoders outperform denoising autoencoders at the very task of denoising, and are competitive with other single-layer techniques on MNIST, and CIFAR-10. We also show that types of noise other than dropout improve performance in a deep network through sparsifying, decorrelating, and spreading information across representations.

自动编码器是无监督学习内部表示的有用框架，本研究将现有的去噪自动编码器扩展到在非线性函数和隐藏单元激活之前注入噪音，提供一种统一的策略来通过设计注入噪声的性质来开发新的内部表示，并表明通过罕见的、去相关、和信息分散的噪声，在深度网络中改善性能。与其他单层技术竞争 MNIST 和 CIFAR-10。

自动编码器和深度网络中的噪声分析