Learning of complex neurons
| dc.contributor.author | Kotsovsky, V. | |
| dc.date.accessioned | 2016-02-23T15:25:30Z | |
| dc.date.available | 2016-02-23T15:25:30Z | |
| dc.date.issued | 2015 | |
| dc.description.abstract | The 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.citation | Kotsovsky 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.uri | https://ena.lpnu.ua/handle/ntb/31307 | |
| dc.language.iso | en | uk_UA |
| dc.publisher | Видавництво Львівської політехніки | uk_UA |
| dc.subject | complex neuron | uk_UA |
| dc.subject | neural network | uk_UA |
| dc.subject | threshold unit | uk_UA |
| dc.subject | threshold function | uk_UA |
| dc.subject | learning | uk_UA |
| dc.title | Learning of complex neurons | uk_UA |
| dc.type | Article | uk_UA |