Sciweavers

869 search results - page 107 / 174
» An Effective Learning Method for Max-Min Neural Networks
Sort
View
IJON
2002
105views more  IJON 2002»
15 years 3 months ago
Separation of sources using simulated annealing and competitive learning
This paper presents a new adaptive procedure for the linear and non-linear separation of signals with non-uniform, symmetrical probability distributions, based on both simulated a...
Carlos García Puntonet, Ali Mansour, Christ...
GECCO
2008
Springer
138views Optimization» more  GECCO 2008»
15 years 5 months ago
Modular neuroevolution for multilegged locomotion
Legged robots are useful in tasks such as search and rescue because they can effectively navigate on rugged terrain. However, it is difficult to design controllers for them that ...
Vinod K. Valsalam, Risto Miikkulainen
ICANN
2007
Springer
15 years 10 months ago
Incremental and Decremental Learning for Linear Support Vector Machines
Abstract. We present a method to find the exact maximal margin hyperplane for linear Support Vector Machines when a new (existing) component is added (removed) to (from) the inner...
Enrique Romero, Ignacio Barrio, Lluís Belan...
IJCNN
2006
IEEE
15 years 10 months ago
Off-line Signature Verification using the Enhanced Modified Direction Feature and Neural-based Classification
—Signatures continue to be an important biometric for authenticating the identity of human beings. This paper presents an effective method to perform off-line signature verificat...
Stephane Armand, Michael Blumenstein, Vallipuram M...
FOCI
2007
IEEE
15 years 10 months ago
Almost All Learning Machines are Singular
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
Sumio Watanabe