Sciweavers

2278 search results - page 296 / 456
» Function-Based Object Recognition
Sort
View
JMLR
2010
192views more  JMLR 2010»
14 years 11 months ago
Efficient Learning of Deep Boltzmann Machines
We present a new approximate inference algorithm for Deep Boltzmann Machines (DBM's), a generative model with many layers of hidden variables. The algorithm learns a separate...
Ruslan Salakhutdinov, Hugo Larochelle
196
Voted
IEEEHPCS
2010
14 years 11 months ago
Calculating the impact factor of neural networks on optimization algorithm for sensor selection
Intelligent sensor selection for monitoring operations is one of the serious subjects to reduce information processing time and increase information fusion accuracy. This paper at...
Abdolhossein Alipoor, Touraj Banirostam, Mehdi N. ...
CVPR
2009
IEEE
1390views Computer Vision» more  CVPR 2009»
16 years 11 months ago
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning
In this paper we present a method for learning classspecific features for recognition. Recently a greedy layerwise procedure was proposed to initialize weights of deep belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
CVPR
2004
IEEE
16 years 6 months ago
Cue Integration through Discriminative Accumulation
Object recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme which extends the...
Maria-Elena Nilsback, Barbara Caputo
ICCV
2001
IEEE
16 years 6 months ago
Robust Histogram Construction from Color Invariants
An effective object recognition scheme is to represent and match images on the basis of histograms derived from photometric color invariants. A drawback, however, is that certain c...
Theo Gevers