Sciweavers

12 search results - page 2 / 3
» Nondeterministic Discretization of Weights Improves Accuracy...
Sort
View
NC
2008
13 years 5 months ago
Top-Down modulation of neural responses in visual perception: a computational exploration
Visual perception is typically performed in the context of a task or goal. Nonetheless, visual processing has traditionally been conceptualized in terms of a fixed, task-independe...
Michael C. Mozer, Adrian Fan
IJCNN
2000
IEEE
13 years 9 months ago
Adding a Healing Mechanism in the Self-Organizing Feature Map Algorithm
It is often reported in the technique literature that the success of the self-organizing feature map (SOM) formation is critically dependent on the initial weights and the selectio...
Mu-Chun Su, Chien-Hsing Chou, Hsiao-Te Chang
ESANN
2006
13 years 6 months ago
Visual object classification by sparse convolutional neural networks
Abstract. A convolutional network architecture termed sparse convolutional neural network (SCNN) is proposed and tested on a real-world classification task (car classification). In...
Alexander Gepperth
TNN
1998
111views more  TNN 1998»
13 years 5 months ago
Asymptotic distributions associated to Oja's learning equation for neural networks
— In this paper, we perform a complete asymptotic performance analysis of the stochastic approximation algorithm (denoted subspace network learning algorithm) derived from Oja’...
Jean Pierre Delmas, Jean-Francois Cardos
IJCNN
2006
IEEE
13 years 11 months ago
Evolutionary Ensemble Creation and Thinning
— Ensembles are often capable of greater predictive accuracy than any of their individual members. One key attribute of ensembles’ success is the notion of diversity. However, ...
Jared Sylvester, Nitesh V. Chawla