Zobrazeno 1 - 10
of 82
pro vyhledávání: '"Călin-Adrian Popa"'
Autor:
Călin-Adrian Popa
Publikováno v:
AIMS Mathematics, Vol 9, Iss 7, Pp 18796-18823 (2024)
Neural networks (NNs) with values in multidimensional domains have lately attracted the attention of researchers. Thus, complex-valued neural networks (CVNNs), quaternion-valued neural networks (QVNNs), and their generalization, Clifford-valued neura
Externí odkaz:
https://doaj.org/article/9b39f0c4cb984f1d91bf5fa7753ec0b7
Autor:
Călin-Adrian Popa
Publikováno v:
AIMS Mathematics, Vol 8, Iss 7, Pp 15969-15992 (2023)
The dynamics of fractional-order neural networks (FONNs) are challenging to study, since the traditional Lyapunov theory does not apply to them. Instead, Halanay-type lemmas are used to create sufficient criteria for specific dynamic properties of FO
Externí odkaz:
https://doaj.org/article/04d5a35c5dd2435080882ca4ac5039fe
Autor:
Călin-Adrian Popa
Publikováno v:
Fractal and Fractional, Vol 7, Iss 11, p 830 (2023)
Very recently, a different generalization of real-valued neural networks (RVNNs) to multidimensional domains beside the complex-valued neural networks (CVNNs), quaternion-valued neural networks (QVNNs), and Clifford-valued neural networks (ClVNNs) ha
Externí odkaz:
https://doaj.org/article/5f039192246e4c0b896dc803d0c8e784
Autor:
Călin-Adrian Popa
Publikováno v:
Fractal and Fractional, Vol 7, Iss 1, p 36 (2022)
The lack of a conventional Lyapunov theory for fractional-order (FO) systems makes it difficult to study the dynamics of fractional-order neural networks (FONNs). Instead, the existing literature derives necessary conditions for various dynamic prope
Externí odkaz:
https://doaj.org/article/0b147d075b854ee884930de9179af344
Publikováno v:
Mathematics, Vol 10, Iss 22, p 4363 (2022)
The latest achievements in the field of reinforcement learning have encouraged the development of vision-based learning methods that compete with human-provided results obtained on various games and training environments. Convolutional neural network
Externí odkaz:
https://doaj.org/article/f5c2f6d7ebaf4544b3b7acc9a280f1fe
Autor:
Călin-Adrian Popa
Publikováno v:
Journal of the Franklin Institute. 360:327-355
Autor:
Călin-Adrian Popa, Eva Kaslik
Publikováno v:
Mathematics, Vol 8, Iss 7, p 1146 (2020)
This paper studies fractional-order neural networks with neutral-type delay, leakage delay, and time-varying delays. A sufficient condition which ensures the finite-time synchronization of these networks based on a state feedback control scheme is de
Externí odkaz:
https://doaj.org/article/ea8d414f53264c50bf23af5c88a29733
Autor:
Călin-Adrian Popa
Publikováno v:
Neurocomputing. 405:85-95
A generalization of real-, complex-, and quaternion-valued neural networks is represented by matrix-valued neural networks (MVNNs), for which the states and weights are matrices. The dissipativity of impulsive MVNNs with leakage delay and mixed delay
Autor:
Călin-Adrian Popa
Publikováno v:
Neurocomputing. 376:73-94
This paper investigates the existence and uniqueness of the equilibrium point and its global µ-stability for neutral-type impulsive complex-valued bidirectional associative memory neural networks with leakage delay and unbounded time-varying delays,
Autor:
Călin-Adrian Popa
Publikováno v:
Neurocomputing. 309:117-133
Octonion-valued neural networks (OVNNs) are a type of neural networks for which the states and weights are octonions. The octonion algebra is the only normed division algebra that can be defined over the reals, besides the complex and quaternion alge