Sciweavers

298 search results - page 44 / 60
» Optimizing number of hidden neurons in neural networks
Sort
View
NN
2002
Springer
136views Neural Networks» more  NN 2002»
13 years 7 months ago
Bayesian model search for mixture models based on optimizing variational bounds
When learning a mixture model, we suffer from the local optima and model structure determination problems. In this paper, we present a method for simultaneously solving these prob...
Naonori Ueda, Zoubin Ghahramani
IJCNN
2000
IEEE
14 years 7 days ago
Using Hopfield Networks to Solve Traveling Salesman Problems Based on Stable State Analysis Technique
In our recent work, a general method called the stable state analysis technique was developed to determine constraints that the weights in the Hopfield energy function must satisf...
Gang Feng, Christos Douligeris
NIPS
1997
13 years 9 months ago
Relative Loss Bounds for Multidimensional Regression Problems
We study on-line generalized linear regression with multidimensional outputs, i.e., neural networks with multiple output nodes but no hidden nodes. We allow at the final layer tra...
Jyrki Kivinen, Manfred K. Warmuth
NN
2000
Springer
161views Neural Networks» more  NN 2000»
13 years 7 months ago
How good are support vector machines?
Support vector (SV) machines are useful tools to classify populations characterized by abrupt decreases in density functions. At least for one class of Gaussian data model the SV ...
Sarunas Raudys
GECCO
1999
Springer
133views Optimization» more  GECCO 1999»
14 years 4 days ago
Evolution of Goal-Directed Behavior from Limited Information in a Complex Environment
In this paper, we apply an evolutionary algorithm to learning behavior on a novel, interesting task to explore the general issue of learning e ective behaviors in a complex enviro...
Matthew R. Glickman, Katia P. Sycara