Sciweavers

916 search results - page 151 / 184
» Using redundancies to find errors
Sort
View
NCA
2006
IEEE
14 years 9 months ago
Evolutionary training of hardware realizable multilayer perceptrons
The use of multilayer perceptrons (MLP) with threshold functions (binary step function activations) greatly reduces the complexity of the hardware implementation of neural networks...
Vassilis P. Plagianakos, George D. Magoulas, Micha...
PRL
2006
95views more  PRL 2006»
14 years 9 months ago
Evolving visual sonar: Depth from monocular images
To recover depth from images, the human visual system uses many monocular depth cues, which vision research has only begun to explore. Because a given image can have many possible...
Martin C. Martin
96
Voted
PAMI
2007
166views more  PAMI 2007»
14 years 9 months ago
A Comparison of Decision Tree Ensemble Creation Techniques
Abstract—We experimentally evaluate bagging and seven other randomizationbased approaches to creating an ensemble of decision tree classifiers. Statistical tests were performed o...
Robert E. Banfield, Lawrence O. Hall, Kevin W. Bow...
ICIP
2010
IEEE
14 years 7 months ago
Improving subpixel stereo matching with segment evolution
Segmentation-based approach has shown significant success in stereo matching. By assuming pixels within one image segment belong to the same 3D surface, robust depth estimation ca...
Yao-Jen Chang, Hung-Hsun Liu, Tsuhan Chen
EMNLP
2010
14 years 7 months ago
Top-Down Nearly-Context-Sensitive Parsing
We present a new syntactic parser that works left-to-right and top down, thus maintaining a fully-connected parse tree for a few alternative parse hypotheses. All of the commonly ...
Eugene Charniak