Lateral Connections in Denoising Autoencoders Support Supervised Learning

Autor:	Rasmus, Antti, Valpola, Harri, Raiko, Tapani
Rok vydání:	2015
Předmět:	Computer Science - Learning Computer Science - Neural and Evolutionary Computing Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	We show how a deep denoising autoencoder with lateral connections can be used as an auxiliary unsupervised learning task to support supervised learning. The proposed model is trained to minimize simultaneously the sum of supervised and unsupervised cost functions by back-propagation, avoiding the need for layer-wise pretraining. It improves the state of the art significantly in the permutation-invariant MNIST classification task.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1504.08215 Zobrazit plný text záznamu View this record from Arxiv