Sciweavers

995 search results - page 178 / 199
» Learning Useful Horn Approximations
Sort
View
159
Voted
NCA
2006
IEEE
15 years 1 months ago
Evolutionary training of hardware realizable multilayer perceptrons
The use of multilayer perceptrons (MLP) with threshold functions (binary step function activations) greatly reduces the complexity of the hardware implementation of neural networks...
Vassilis P. Plagianakos, George D. Magoulas, Micha...
98
Voted
TNN
1998
96views more  TNN 1998»
15 years 1 months ago
Noise suppressing sensor encoding and neural signal orthonormalization
In this paper we regard first the situation where parallel channels are disturbed by noise. With the goal of maximal information conservation we deduce the conditions for a transf...
Rüdiger W. Brause, M. Rippl
140
Voted
TEC
2008
135views more  TEC 2008»
15 years 1 months ago
Evolving Output Codes for Multiclass Problems
In this paper, we propose an evolutionary approach to the design of output codes for multiclass pattern recognition problems. This approach has the advantage of taking into account...
Nicolás García-Pedrajas, Colin Fyfe
117
Voted
ICSOC
2010
Springer
15 years 11 days ago
From Quality to Utility: Adaptive Service Selection Framework
Abstract. We consider an approach to service selection wherein service consumers choose services with desired nonfunctional properties to maximize their utility. A consumer’s uti...
Chung-Wei Hang, Munindar P. Singh
174
Voted
IGARSS
2010
14 years 8 months ago
Calibrating probabilities for hyperspectral classification of rock types
This paper investigates the performance of machine learning methods for classifying rock types from hyperspectral data. The main objective is to test the impact on classification ...
Sildomar T. Monteiro, Richard J. Murphy