An efficient training algorithm for dynamic synapse neural networks using trust region methods.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 12850011.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
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.
Medical subject headings
- Algorithms
- Neural Networks, Computer
- Synapses