PROBABILISTIC PROPERTIES OF THE INITIAL VALUES OF WEIGHTING FACTORS IN SYNCHRONIZED ARTIFICIAL NEURAL
One of the most efficient ways for identical binary se quences generation is using methods of neural cryptography. The initial weight vestors values influence on speed of synchronization is analized. Equal probability of initial weight vestors motion directions is great advantage. On this base autho...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Belarusian National Technical University
2015-05-01
|
| Series: | Sistemnyj Analiz i Prikladnaâ Informatika |
| Online Access: | https://sapi.bntu.by/jour/article/view/11 |
| _version_ | 1797873761600405504 |
|---|---|
| author | V. F. Golikov N. V. Brich |
| author_facet | V. F. Golikov N. V. Brich |
| author_sort | V. F. Golikov |
| collection | DOAJ |
| description | One of the most efficient ways for identical binary se quences generation is using methods of neural cryptography. The initial weight vestors values influence on speed of synchronization is analized. Equal probability of initial weight vestors motion directions is great advantage. On this base authors suppose new line of research conserned with improvement of network architecture and correction algorithm. |
| first_indexed | 2024-04-10T01:20:14Z |
| format | Article |
| id | doaj.art-0759b6549256458c8c5b505ab9fb56db |
| institution | Directory Open Access Journal |
| issn | 2309-4923 2414-0481 |
| language | English |
| last_indexed | 2024-04-10T01:20:14Z |
| publishDate | 2015-05-01 |
| publisher | Belarusian National Technical University |
| record_format | Article |
| series | Sistemnyj Analiz i Prikladnaâ Informatika |
| spelling | doaj.art-0759b6549256458c8c5b505ab9fb56db2023-03-13T09:47:39ZengBelarusian National Technical UniversitySistemnyj Analiz i Prikladnaâ Informatika2309-49232414-04812015-05-0101-233375PROBABILISTIC PROPERTIES OF THE INITIAL VALUES OF WEIGHTING FACTORS IN SYNCHRONIZED ARTIFICIAL NEURALV. F. Golikov0N. V. Brich1Белорусский национальный технический университетБелорусский национальный технический университетOne of the most efficient ways for identical binary se quences generation is using methods of neural cryptography. The initial weight vestors values influence on speed of synchronization is analized. Equal probability of initial weight vestors motion directions is great advantage. On this base authors suppose new line of research conserned with improvement of network architecture and correction algorithm.https://sapi.bntu.by/jour/article/view/11 |
| spellingShingle | V. F. Golikov N. V. Brich PROBABILISTIC PROPERTIES OF THE INITIAL VALUES OF WEIGHTING FACTORS IN SYNCHRONIZED ARTIFICIAL NEURAL Sistemnyj Analiz i Prikladnaâ Informatika |
| title | PROBABILISTIC PROPERTIES OF THE INITIAL VALUES OF WEIGHTING FACTORS IN SYNCHRONIZED ARTIFICIAL NEURAL |
| title_full | PROBABILISTIC PROPERTIES OF THE INITIAL VALUES OF WEIGHTING FACTORS IN SYNCHRONIZED ARTIFICIAL NEURAL |
| title_fullStr | PROBABILISTIC PROPERTIES OF THE INITIAL VALUES OF WEIGHTING FACTORS IN SYNCHRONIZED ARTIFICIAL NEURAL |
| title_full_unstemmed | PROBABILISTIC PROPERTIES OF THE INITIAL VALUES OF WEIGHTING FACTORS IN SYNCHRONIZED ARTIFICIAL NEURAL |
| title_short | PROBABILISTIC PROPERTIES OF THE INITIAL VALUES OF WEIGHTING FACTORS IN SYNCHRONIZED ARTIFICIAL NEURAL |
| title_sort | probabilistic properties of the initial values of weighting factors in synchronized artificial neural |
| url | https://sapi.bntu.by/jour/article/view/11 |
| work_keys_str_mv | AT vfgolikov probabilisticpropertiesoftheinitialvaluesofweightingfactorsinsynchronizedartificialneural AT nvbrich probabilisticpropertiesoftheinitialvaluesofweightingfactorsinsynchronizedartificialneural |