Sciweavers

116 search results - page 18 / 24
» Neural Networks Training with Optimal Bounded Ellipsoid Algo...
Sort
View
IJCNN
2006
IEEE
14 years 1 months ago
A Heuristic for Free Parameter Optimization with Support Vector Machines
— A heuristic is proposed to address free parameter selection for Support Vector Machines, with the goals of improving generalization performance and providing greater insensitiv...
Matthew Boardman, Thomas P. Trappenberg
ICANN
2009
Springer
14 years 2 months ago
Evolving Memory Cell Structures for Sequence Learning
The best recent supervised sequence learning methods use gradient descent to train networks of miniature nets called memory cells. The most popular cell structure seems somewhat ar...
Justin Bayer, Daan Wierstra, Julian Togelius, J&uu...
DMIN
2006
126views Data Mining» more  DMIN 2006»
13 years 9 months ago
Comparison and Analysis of Mutation-based Evolutionary Algorithms for ANN Parameters Optimization
Mutation-based Evolutionary Algorithms, also known as Evolutionary Programming (EP) are commonly applied to Artificial Neural Networks (ANN) parameters optimization. This paper pre...
Kristina Davoian, Alexander Reichel, Wolfram-Manfr...
EUSFLAT
2003
122views Fuzzy Logic» more  EUSFLAT 2003»
13 years 9 months ago
Structure recognition on sequences with a neuro-fuzzy-system
We present a formal description of a neurofuzzy system capable of aligning two sequences recognizing their internal structure. The alignment is done on two levels: grouping of the...
Klaus Dalinghaus, Tillman Weyde
WSC
2007
13 years 9 months ago
Allocation of simulation runs for simulation optimization
Simulation optimization (SO) is the process of finding the optimum design of a system whose performance measure(s) are estimated via simulation. We propose some ideas to improve o...
Alireza Kabirian, Sigurdur Ólafsson