15 search results - page 1 / 3 » Deep networks for robust visual recognition |
ICML
2010
IEEE
13 years 6 months ago
2010
IEEE
Deep Belief Networks (DBNs) are hierarchical generative models which have been used successfully to model high dimensional visual data. However, they are not robust to common vari...
NIPS
2008
13 years 6 months ago
2008
In this paper we aim to train deep neural networks for rapid visual recognition. The task is highly challenging, largely due to the lack of a meaningful regularizer on the functio...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
In this paper, we extend the work done on integrating multilayer perceptron (MLP) networks with HMM systems via the Tandem approach. In particular, we explore whether the use of D...
JMLR
2012
11 years 7 months ago
2012
Motivated by the observation that coarse and fine resolutions of an image reveal different structures in the underlying visual phenomenon, we present a model based on the Deep B...
ICML
2009
IEEE
14 years 5 months ago
2009
IEEE
There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks. Scaling such models to full-sized, high-dimensional images re...