371 search results - page 5 / 75 » Competitive Neural Network Training: A Multi-Resolution Appr... |
100
Voted
ICML
2008
IEEE
16 years 2 months ago
2008
IEEE
Recently, many applications for Restricted Boltzmann Machines (RBMs) have been developed for a large variety of learning problems. However, RBMs are usually used as feature extrac...
106
click to vote
TNN
2008
15 years 1 months ago
2008
In this paper, a supervised neural network training technique based on constrained optimization is developed for preserving prior knowledge of an input
141
click to vote
KSEM
2009
Springer
15 years 8 months ago
2009
Springer
Abstract. Support Vector Machines (SVM) have been applied successfully in a wide variety of fields in the last decade. The SVM problem is formulated as a convex objective function...
113
Voted
IJON
2000
2000
Synthesis approach for bidirectional associative memories based on the perceptron training algorithm
15 years 1 months ago
Bidirectional associative memories are being used extensively for solving a variety of problems related to pattern recognition. In the present paper, a new synthesis approach is d...
164
click to vote
TSMC
2002
15 years 1 months ago
2002
The Al-Alaoui algorithm is a weighted mean-square error (MSE) approach to pattern recognition. It employs cloning of the erroneously classified samples to increase the population o...