Sciweavers

2924 search results - page 205 / 585
» On the Use of Evidence in Neural Networks
Sort
View
ECIS
2000
15 years 7 months ago
Information Filtering and Automatic Keyword Identification by Artificial Neural Networks
Information filtering (IF) systems usually filter data items by correlating a vector of terms (keywords) that represent the user profile with similar vectors of terms that represe...
Zvi Boger, Tsvi Kuflik, Bracha Shapira, Peretz Sho...
IJCNN
2006
IEEE
16 years 16 days 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...
FLAIRS
2010
15 years 8 months ago
CsMTL MLP For WEKA: Neural Network Learning with Inductive Transfer
We present context-sensitive Multiple Task Learning, or csMTL as a method of inductive transfer. It uses additional contextual inputs along with other input features when learning ...
Liangliang Tu, Benjamin Fowler, Daniel L. Silver
ESANN
2006
15 years 8 months ago
Designing neural network committees by combining boosting ensembles
The use of modified Real Adaboost ensembles by applying weighted emphasis on erroneous and critical (near the classification boundary) has been shown to lead to improved designs, ...
Vanessa Gómez-Verdejo, Aníbal R. Fig...
GECCO
2010
Springer
181views Optimization» more  GECCO 2010»
15 years 11 months ago
Evolving neural networks in compressed weight space
We propose a new indirect encoding scheme for neural networks in which the weight matrices are represented in the frequency domain by sets of Fourier coefficients. This scheme exp...
Jan Koutnik, Faustino J. Gomez, Jürgen Schmid...