39 search results - page 1 / 8 » Improving generalization capability of neural networks based... |
CEC
2007
IEEE
13 years 11 months ago
2007
IEEE
— This paper presents a single-objective and a multiobjective stochastic optimization algorithms for global training of neural networks based on simulated annealing. The algorith...
WSC
2004
13 years 6 months ago
2004
Adaptive neural network is a powerful tool for prediction of air pollution abatement scenarios. But it is often difficult to avoid overfit during the training of adaptive neural n...
IJCNN
2000
IEEE
13 years 9 months ago
2000
IEEE
In our recent work, a general method called the stable state analysis technique was developed to determine constraints that the weights in the Hopfield energy function must satisf...
KES
2005
Springer
13 years 10 months ago
2005
Springer
With a continuing improvement in the capabilities of intelligence per unit of energy, we should reconsider the organisation of sensor networks. We contend that solutions should be ...
IJCNN
2006
IEEE
13 years 11 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...