Abstract | ||
---|---|---|
The neural-net-similar associative memory model NEUNET is able to store and reproduce patterns reading from its receptors. This article describes an enhancement of the model to associate faulty or incomplete inputs with weighted original patterns. The network is self-learning, the correction of inputs, the storage of new information and the calculation of weights which enables the model to store information with various priorities is self-organized. Priority of information is increased if it is frequently used and consequently in case of the association of unknown inputs it is more like to be associated with a high-priority original pattern. This selective behavior is the main enhancement of the model described in this contribution. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-75867-9_111 | EUROCAST |
Keywords | Field | DocType |
selective association,high-priority original pattern,unknown input,neural-net-similar associative memory model,main enhancement,weighted original pattern,selective behavior,various priority,model neunet,new information,incomplete input,self organization,artificial intelligent,neural net,artificial intelligence,neural network,associative memory | Content-addressable memory,Associative property,Computer science,Bidirectional associative memory,Theoretical computer science,Artificial intelligence,Artificial neural network,Machine learning | Conference |
Volume | ISSN | ISBN |
4739 | 0302-9743 | 3-540-75866-6 |
Citations | PageRank | References |
0 | 0.34 | 3 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Reinhard Stumptner | 1 | 9 | 4.56 |
Josef Küng | 2 | 523 | 59.90 |