50 search results - page 1 / 10 » Deep Learning with Kernel Regularization for Visual Recognit... |
NIPS
2008
13 years 5 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...
ICML
2008
IEEE
14 years 5 months ago
2008
IEEE
We show how nonlinear embedding algorithms popular for use with shallow semisupervised learning techniques such as kernel methods can be applied to deep multilayer architectures, ...
ICML
2010
IEEE
13 years 5 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...
CVPR
2007
IEEE
13 years 10 months ago
2007
IEEE
This paper describes a local ensemble kernel learning technique to recognize/classify objects from a large number of diverse categories. Due to the possibly large intraclass featu...
ICPR
2008
IEEE
13 years 10 months ago
2008
IEEE
Robustness is one of the most critical issues in the appearance-based learning strategies. In this work, we propose a novel kernel that is robust against data corruption for vario...