187
click to vote
IJCNN
2000
IEEE
16 years 2 days ago
2000
IEEE
Bayesian MLP neural networks are a flexible tool in complex nonlinear problems. The approach is complicated by need to evaluate integrals over high-dimensional probability distri...
200
Voted
IJCNN
2000
IEEE
16 years 2 days ago
2000
IEEE
The main purpose of this paper is to compare the support vector machine (SVM) developed by Vapnik with other techniques such as Backpropagation and Radial Basis Function (RBF) Net...
146
click to vote
IJCNN
2000
IEEE
2000
IEEE
Pulse-Coupled Networks of Non-Autonomous Integrate-and-Fire Oscillators and Classification Functions
16 years 2 days ago
198
click to vote
IJCNN
2000
IEEE
16 years 2 days ago
2000
IEEE
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...
217
click to vote
IJCNN
2000
IEEE
16 years 2 days ago
2000
IEEE
We propose to solve a text categorization task using a new metric between documents, based on a priori semantic knowledge about words. This metric can be incorporated into the def...
187
Voted
IJCNN
2000
IEEE
16 years 2 days ago
2000
IEEE
: The main purpose of this work is to create a physiologically realistic computational model of the retina by providing a flexible, real-valued three-dimensional architecture. This...
150
Voted
IJCNN
2000
IEEE
16 years 2 days ago
2000
IEEE
143
click to vote
IJCNN
2000
IEEE
16 years 2 days ago
2000
IEEE
KBCC is an extension of the cascade-correlation algorithm that treats functions encapsulating prior knowledge as black-boxes which, like simple sigmoidal neurons, can be recruited...
180
Voted
IJCNN
2000
IEEE
16 years 2 days ago
2000
IEEE
199
Voted
IJCNN
2000
IEEE
16 years 2 days ago
2000
IEEE
The problem of designing input signals for optimal generalization in supervised learning is called active learning. In many active learning methods devised so far, the bias of the...