Title :
Trust region nonlinear optimization learning method for dynamic synapse neural networks
Author :
Narnarvar, H.H. ; Berger, Theodore W.
Author_Institution :
Dept. of Biomed. Eng., Univ. of Southern California, Los Angeles, CA, USA
Abstract :
We formulate the dynamic synapse neural network from the averaged activity of local population of neurons perspective. We have applied the trust region nonlinear optimization approach to train the network and show the new learning method effectiveness in comparison to the genetic algorithms by optimizing large-scale networks.
Keywords :
learning (artificial intelligence); neural nets; nonlinear programming; averaged activity; dynamic synapse neural networks; large-scale network optimization; learning method effectiveness; local population; trust region nonlinear optimization approach; trust region nonlinear optimization learning method; Artificial neural networks; Biological neural networks; Biological system modeling; Genetic algorithms; Large-scale systems; Learning systems; Neural networks; Neurons; Optimization methods; Signal processing algorithms;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1224023
