On the exact relationship between the denoising function and the data distribution

Autor:	Arponen, Heikki, Herranen, Matti, Valpola, Harri
Rok vydání:	2017
Předmět:	Computer Science - Neural and Evolutionary Computing Computer Science - Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	We prove an exact relationship between the optimal denoising function and the data distribution in the case of additive Gaussian noise, showing that denoising implicitly models the structure of data allowing it to be exploited in the unsupervised learning of representations. This result generalizes a known relationship [2], which is valid only in the limit of small corruption noise. Comment: 4 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1709.02797 Zobrazit plný text záznamu View this record from Arxiv