Source:http://linkedlifedata.com/resource/pubmed/id/11414980
Switch to
| Predicate | Object |
|---|---|
| rdf:type | |
| lifeskim:mentions | |
| pubmed:issue |
5 Pt 2
|
| pubmed:dateCreated |
2001-6-20
|
| pubmed:abstractText |
A perceptron that "learns" the opposite of its own output is used to generate a time series. We analyze properties of the weight vector and the generated sequence, such as the cycle length and the probability distribution of generated sequences. A remarkable suppression of the autocorrelation function is explained, and connections to the Bernasconi model are discussed. If a continuous transfer function is used, the system displays chaotic and intermittent behavior, with the product of the learning rate and amplification as a control parameter.
|
| pubmed:language |
eng
|
| pubmed:journal | |
| pubmed:status |
PubMed-not-MEDLINE
|
| pubmed:month |
May
|
| pubmed:issn |
1539-3755
|
| pubmed:author | |
| pubmed:issnType |
Print
|
| pubmed:volume |
63
|
| pubmed:owner |
NLM
|
| pubmed:authorsComplete |
Y
|
| pubmed:pagination |
056126
|
| pubmed:year |
2001
|
| pubmed:articleTitle |
Generation of unpredictable time series by a neural network.
|
| pubmed:affiliation |
Institut für Theoretische Physik, Universität Würzburg, Am Hubland, D-97074 Würzburg, Germany.
|
| pubmed:publicationType |
Journal Article
|