SSM: A Statistical Stepwise Method for Weight Elimination

Cottrell, Marie; Girard, B.; Girard, Y.; Mangeas, Morgan; Müller, Christian

doi:10.1007/978-1-4471-2097-1_160

Cited by 7 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The specification of the operators for candidate solution generation is essential for the methods' success. Differently from Yamazaki and Ludemir's approach [6] and from some known pruning algorithms [7][8] [9], the proposed method does not operate at the connection level for MLP topology optimization; it works at the neuron level, instead. This apparently simple change drastically reduces the size of the solution search space.…”

Section: Generation Of Candidate Solutionsmentioning

confidence: 99%

Hybrid Approach for Time Series Prediction using Neural Networks and Simulated Annealing

Arnaud

Adeodato

Vasconcelos

et al. 2016

Anais Do 7. Congresso Brasileiro De Redes Neurais

View full text Add to dashboard Cite

This paper proposes a new hybrid approach which combines simulated annealing and standard backpropagation for optimizing Multi Layer Perceptron Neural Networks (MLP) for time series prediction. Experimental tests were carried out on four simulated series with known features and on the Sunspot series. The results have shown that this approach selects the appropriate time series lags and builds an MLP with the minimum number of hidden neurons required for achieving good performance on the task. The performance attained was better than some results recently reported for hybrid systems combining Genetic Algorithms (GA) and MLPs for the same purpose presented here.

show abstract

Section: Generation Of Candidate Solutionsmentioning

confidence: 99%