Sciweavers

409 search results - page 27 / 82
» Representation of Functional Data in Neural Networks
Sort
View
107
Voted
NPL
2006
172views more  NPL 2006»
14 years 10 months ago
Adapting RBF Neural Networks to Multi-Instance Learning
In multi-instance learning, the training examples are bags composed of instances without labels, and the task is to predict the labels of unseen bags through analyzing the training...
Min-Ling Zhang, Zhi-Hua Zhou
67
Voted
IJCNN
2008
IEEE
15 years 4 months ago
Learning associations of conjuncted fuzzy sets for data prediction
— Fuzzy Associative Conjuncted Maps (FASCOM) is a fuzzy neural network that represents information by conjuncting fuzzy sets and associates them through a combination of unsuperv...
Hanlin Goh, Joo-Hwee Lim, Chai Quek
67
Voted
ICPR
2002
IEEE
15 years 11 months ago
Self-Calibration and Neural Network Implementation of Photometric Stereo
This paper describes a new approach to neural network implementation of photometric stereo for a rotational object with non-uniform reflectance factor. Three input images are acqu...
Yuji Iwahori, Yumi Watanabe, Robert J. Woodham, Ak...
82
Voted
TNN
1998
123views more  TNN 1998»
14 years 9 months ago
A general framework for adaptive processing of data structures
—A structured organization of information is typically required by symbolic processing. On the other hand, most connectionist models assume that data are organized according to r...
Paolo Frasconi, Marco Gori, Alessandro Sperduti
83
Voted
ISNN
2005
Springer
15 years 3 months ago
Scaling the Kernel Function to Improve Performance of the Support Vector Machine
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...
Peter Williams, Sheng Li, Jianfeng Feng, Si Wu