Sciweavers

640 search results - page 4 / 128
» Extracting Propositions from Trained Neural Networks
Sort
View
IJCNN
2000
IEEE
13 years 11 months ago
Sensitivity Analysis for Conic Section Function Neural Networks
Sensitivity analysis is a method for extracting the cause and effect relationship between the inputs and outputs of the network. After training a neural network, one may want to k...
Lale Özyilmaz, Tülay Yildirim
TNN
2010
234views Management» more  TNN 2010»
13 years 2 months ago
Novel maximum-margin training algorithms for supervised neural networks
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
Oswaldo Ludwig, Urbano Nunes
ESANN
2003
13 years 8 months ago
A new rule extraction algorithm based on interval arithmetic
In this paper we propose a new algorithm for rule extraction from a trained Multilayer Feedforward network. The algorithm is based on an interval arithmetic network inversion for p...
Carlos Hernández-Espinosa, Mercedes Fern&aa...
CVPR
2012
IEEE
11 years 9 months ago
Enhanced continuous sign language recognition using PCA and neural network features
In this work a Gaussian Hidden Markov Model (GHMM) based automatic sign language recognition system is built on the SIGNUM database. The system is trained on appearance-based feat...
Yannick L. Gweth, Christian Plahl, Hermann Ney
FUZZY
2001
Springer
121views Fuzzy Logic» more  FUZZY 2001»
13 years 12 months ago
Interpretation of Trained Neural Networks by Rule Extraction
Vasile Palade, Ciprian-Daniel Neagu, Ronald J. Pat...