Sciweavers

105 search results - page 9 / 21
» nn 2010
Sort
View
ICANN
2010
Springer
14 years 7 months ago
Using Evolutionary Multiobjective Techniques for Imbalanced Classification Data
The aim of this paper is to study the use of Evolutionary Multiobjective Techniques to improve the performance of Neural Networks (NN). In particular, we will focus on classificati...
Sandra García, Ricardo Aler, Inés Ma...
DM
2010
134views more  DM 2010»
14 years 9 months ago
The discrepancy of the lex-least de Bruijn sequence
We answer the following question of R. L. Graham: What is the discrepancy of the lexicographically-least binary de Bruijn sequence? Here, "discrepancy" refers to the max...
Joshua Cooper, Christine E. Heitsch
NN
2010
Springer
225views Neural Networks» more  NN 2010»
14 years 8 months ago
Learning to imitate stochastic time series in a compositional way by chaos
This study shows that a mixture of RNN experts model can acquire the ability to generate sequences that are combination of multiple primitive patterns by means of self-organizing ...
Jun Namikawa, Jun Tani
NN
2010
Springer
183views Neural Networks» more  NN 2010»
14 years 8 months ago
Dimensionality reduction for density ratio estimation in high-dimensional spaces
The ratio of two probability density functions is becoming a quantity of interest these days in the machine learning and data mining communities since it can be used for various d...
Masashi Sugiyama, Motoaki Kawanabe, Pui Ling Chui
NN
2010
Springer
125views Neural Networks» more  NN 2010»
14 years 8 months ago
Parameter-exploring policy gradients
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in paramet...
Frank Sehnke, Christian Osendorfer, Thomas Rü...