Home
Deutsch
Advanced Search
Browse by ...
Publication overview
Contact persons
Help
 |
|
Open Access Green as soon as Postprint is submitted to ZB.
Associative Neural Network.
Methods Mol. Biol. 458, 187-204 (2008)
An associative neural network (ASNN) is an ensemble-based method inspired by the function and structure of neural network correlations in brain. The method operates by simulating the short- and long-term memory of neural networks. The long-term memory is represented by ensemble of neural network weights, while the short-term memory is stored as a pool of internal neural network representations of the input pattern. The organization allows the ASNN to incorporate new data cases in short-term memory and provides high generalization ability without the need to retrain the neural network weights. The method can be used to estimate a bias and the applicability domain of models. Applications of the ASNN in QSAR and drug design are exemplified.
Additional Metrics?
Edit extra informations
Login
Publication type
Article: Journal article
Document type
Scientific Article
Editors
Livingstone, D.S.*
Keywords
ensemble networks; memory; drug design; LIBRARY mode
ISSN (print) / ISBN
1064-3745
e-ISSN
1940-6029
Conference Title
Artitificial Neural Networks: Methods and Applications
Journal
Methods in Molecular Biology
Quellenangaben
Volume: 458,
Pages: 187-204
Series
Methods in Molecular Biology
Publisher
Springer
Publishing Place
Berlin [u.a.]
Reviewing status
Peer reviewed