Sciweavers

1160 search results - page 15 / 232
» Dynamic Programming Algorithm for Training Functional Networ...
Sort
View
JMLR
2010
151views more  JMLR 2010»
13 years 3 months ago
Understanding the difficulty of training deep feedforward neural networks
Whereas before 2006 it appears that deep multilayer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with e...
Xavier Glorot, Yoshua Bengio
ECCV
2000
Springer
14 years 10 months ago
Diffeomorphic Matching Problems in One Dimension: Designing and Minimizing Matching Functionals
This paper focuses on matching 1D structures by variational methods. We provide rigorous rules for the construction of the cost function, on the basis of an analysis of properties ...
Alain Trouvé, Laurent Younes
ICPR
2010
IEEE
13 years 7 months ago
Incremental Training of Multiclass Support Vector Machines
We present a new method for the incremental training of multiclass Support Vector Machines that provides computational efficiency for training problems in the case where the trai...
Symeon Nikitidis, Nikos Nikolaidis, Ioannis Pitas
GPEM
2006
89views more  GPEM 2006»
13 years 8 months ago
Morphological algorithm design for binary images using genetic programming
This paper presents a Genetic Programming (GP) approach to the design of Mathematical Morphology (MM) algorithms for binary images. The algorithms are constructed using logic opera...
Marcos I. Quintana, Riccardo Poli, Ela Claridge
IWCMC
2010
ACM
13 years 6 months ago
Dynamic load balancing and throughput optimization in 3GPP LTE networks
Load imbalance that deteriorates the system performance is a severe problem existing in 3GPP LTE networks. To deal with this problem, we propose in this paper a load balancing fra...
Hao Wang, Lianghui Ding, Ping Wu, Zhiwen Pan, Nan ...