374 search results - page 48 / 75 » Training the random neural network using quasi-Newton method... |
101
click to vote
ICANN
2007
Springer
15 years 3 months ago
2007
Springer
Meta-Learning has been used to select algorithms based on the features of the problems being tackled. Each training example in this context, i.e. each meta-example, stores the feat...
144
click to vote
AR
2011
14 years 6 months ago
2011
We propose a real-time pose invariant face recognition algorithm from a gallery of frontal images only. First, we modified the second order minimization method for active appearan...
ICNC
2005
Springer
15 years 5 months ago
2005
Springer
In this paper we firstly analysis the chaotic characters of three sets of the financial time series (Hang Sheng Index (HIS), Shanghai Stock Index and US gold price) based on the ph...
ISNN
2005
Springer
15 years 5 months ago
2005
Springer
Abstract. The present study investigates a geometrical method for optimizing the kernel function of a support vector machine. The method is an improvement of the one proposed in [4...
108
click to vote
ESANN
2006
15 years 1 months ago
2006
In this article, we extend a local prototype-based learning model by active learning, which gives the learner the capability to select training samples during the model adaptation...