Learning of complex neurons

dc.contributor.authorKotsovsky, V.
dc.date.accessioned2016-02-23T15:25:30Z
dc.date.available2016-02-23T15:25:30Z
dc.date.issued2015
dc.description.abstractThe paper deals with the problems of realization of Boolean functions on neural-like units with complex weight coefficients. The relation between classes of realizable function is considered for half-plane-like activation function. We also introduce the concept of sets separability, corresponding to our notion of neuron. The iterative online learning algorithm is proposed and sufficient conditions of its convergence are given.uk_UA
dc.identifier.citationKotsovsky V. Learning of complex neurons / V. Kotsovsky // Вісник Національного університету "Львівська політехніка". Серія: Комп’ютерні науки та інформаційні технології : збірник наукових праць. – 2015. – № 826. – С. 131–135. – Bibliography: 5 titles.uk_UA
dc.identifier.urihttps://ena.lpnu.ua/handle/ntb/31307
dc.language.isoenuk_UA
dc.publisherВидавництво Львівської політехнікиuk_UA
dc.subjectcomplex neuronuk_UA
dc.subjectneural networkuk_UA
dc.subjectthreshold unituk_UA
dc.subjectthreshold functionuk_UA
dc.subjectlearninguk_UA
dc.titleLearning of complex neuronsuk_UA
dc.typeArticleuk_UA

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
19-131-135.pdf
Size:
618.27 KB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: