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: | V. F. Golikov, N. V. Brich |
---|---|
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 |
Similar Items
-
Common Secret Key Derivation Based on Synchronized Artificial Neuronal Networks Using Multispeed Weighted Coefficients Correction
by: V. F. Golikov, et al.
Published: (2019-06-01) -
Attack on synchronized artificial neural networks, forming a common secret by deferred search
by: V. F. Golikov, et al.
Published: (2019-06-01) -
Combined formаtion of a cryptographic key using synchronized artificial neural networks
by: M. L. Radziukevich, et al.
Published: (2021-02-01) -
Enhancing the secrecy of a cryptographic key generated using synchronized artificial neural networks1
by: M. L. Radziukevich, et al.
Published: (2020-03-01) -
Effect of Initial Configuration of Weights on Training and Function of Artificial Neural Networks
by: Ricardo J. Jesus, et al.
Published: (2021-09-01)