IJCNN
2006
IEEE
14 years 6 months ago
2006
IEEE
— Several heuristic methods have been suggested for improving the generalization capability in neural network learning, most of which are concerned with a single-objective (SO) l...
IJCNN
2006
IEEE
14 years 6 months ago
2006
IEEE
Abstract— In previous work, we have shown that both unsupervised feature selection and the semi-supervised clustering problem can be usefully formulated as multiobjective optimiz...
IJCNN
2006
IEEE
14 years 6 months ago
2006
IEEE
– When subjected to transient disturbances in the power grid, the variable frequency converter (VFC) is the most sensitive part in the variable-speed wind turbine generator syste...
IJCNN
2006
IEEE
14 years 6 months ago
2006
IEEE
— The optimization of classification systems is often confronted by the solution over-fit problem. Solution over-fit occurs when the optimized classifier memorizes the traini...
IJCNN
2006
IEEE
14 years 6 months ago
2006
IEEE
— This paper argues that connectionist systems are a good approach to implement a speech understanding computational model. In this direction, we propose SUM, a Speech Understand...
IJCNN
2006
IEEE
14 years 6 months ago
2006
IEEE
— Neuronal activities related to context-dependent recall have been found in the monkey inferotemporal cortex. If we set the same task for an artificial neural network, however,...
IJCNN
2006
IEEE
14 years 6 months ago
2006
IEEE
— Defensive islanding is an efficient way to avoid catastrophic failures and wide area blackouts. Power system splitting especially for large scale power systems is a combinatori...
IJCNN
2006
IEEE
14 years 6 months ago
2006
IEEE
—Event-related potentials (ERPs) recorded at the scalp are indicators of brain activity associated with eventrelated information processing; hence they may be suitable for the as...
IJCNN
2006
IEEE
14 years 6 months ago
2006
IEEE
Abstract— The incomplete information about the Web structure causes inaccurate results of various ranking algorithms. In this paper, we propose a solution to this problem by form...
IJCNN
2006
IEEE
14 years 6 months ago
2006
IEEE
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...