Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Andrich B. van Wyk"'
Publikováno v:
CEC
Previous studies of feedforward neural networks (FFNNs) have found that asymptotically bounded activation functions used by particle swarm optimised (PSO) FFNNs have a significant impact on the swarm behaviour and FFNN performance. A number of altern
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::91a2ee57c0ca54003b7075d8c5df3803
https://doi.org/10.1109/cec.2016.7743825
https://doi.org/10.1109/cec.2016.7743825
Publikováno v:
SWIS
This paper investigates the performance of a dynamic heterogeneous particle swarm optimizer (dHPSO) on dynamic unconstrained optimization problems. The results are compared to that of charged and quantum particle swarms, specifically designed for opt
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::da7cbcace365368f4f62d155e9fc502c
https://doi.org/10.1109/sis.2011.5952564
https://doi.org/10.1109/sis.2011.5952564
Publikováno v:
SWIS
The sigmoid function is a widely used, bounded activation function for feedforward neural networks (FFNNs). A problem with using bounded activation functions is that it necessitates scaling of the data to suit the fixed domain and range of the functi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::51bef099bd1e1e0483130e5ae541d4cd
https://doi.org/10.1109/sis.2011.5952561
https://doi.org/10.1109/sis.2011.5952561
Publikováno v:
IEEE Congress on Evolutionary Computation
The purpose of this paper is to investigate the overfitting behavior of particle swarm optimization (PSO) trained neural networks. Neural networks trained with PSOs using the global best, local best and Von Neumann information sharing topologies are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6b3f761be15853b228ed342f31e1a9e0
https://doi.org/10.1109/cec.2010.5586333
https://doi.org/10.1109/cec.2010.5586333