Resolution of singularities via deep complex-valued neural networks
Sign Up to like & getrecommendations! Published in 2018 at "Mathematical Methods in The Applied Sciences"
DOI: 10.1002/mma.4434
Abstract: It has been reported that training deep neural networks is more difficult than training shallow neural networks. Hinton et al. proposed deep belief networks with a learning algorithm that trains one layer at a time. A… read more here.
Keywords: valued neural; deep neural; neural networks; singular points ... See more keywords
Convergence of Quasi-Newton Method for Fully Complex-Valued Neural Networks
Sign Up to like & getrecommendations! Published in 2017 at "Neural Processing Letters"
DOI: 10.1007/s11063-017-9621-7
Abstract: In this paper, based on Wirtinger calculus, we introduce a quasi-Newton method for training complex-valued neural networks with analytic activation functions. Using the duality between Wirtinger calculus and multivariate real calculus, we prove a convergence… read more here.
Keywords: valued neural; method; quasi newton; newton method ... See more keywords
Robust State Estimation for Delayed Complex-Valued Neural Networks
Sign Up to like & getrecommendations! Published in 2017 at "Neural Processing Letters"
DOI: 10.1007/s11063-017-9626-2
Abstract: This paper is concerned with the state estimation problem for the uncertain complex-valued neural networks with time delays. The parameter uncertainties are assumed to be norm-bounded. Through available output measurements containing nonlinear Lipschitz-like terms, we… read more here.
Keywords: state; valued neural; neural networks; state estimation ... See more keywords
Synchronization Control of Quaternion-Valued Neural Networks with Parameter Uncertainties
Sign Up to like & getrecommendations! Published in 2019 at "Neural Processing Letters"
DOI: 10.1007/s11063-019-10153-2
Abstract: In this paper, by starting from basic quaternion algebra properties and algorithms, we develop a comprehensive set of properties to ensure the uncertain quaternion-valued neural networks can receive synchronization and quasi-synchronization goals. By endowing the… read more here.
Keywords: quaternion; valued neural; neural networks; control ... See more keywords
Synchronization in Quaternion-Valued Neural Networks with Delay and Stochastic Impulses
Sign Up to like & getrecommendations! Published in 2022 at "Neural Processing Letters"
DOI: 10.1007/s11063-021-10653-0
Abstract: A class of global exponential synchronization problem for delayed quaternion-valued neural networks with stochastic impulses has been investigated in this paper, where the impulses arouse time and strength both are randomly. Firstly, the delayed quaternion-valued… read more here.
Keywords: quaternion valued; valued neural; neural networks; stochastic impulses ... See more keywords
Lagrange stability analysis for complex-valued neural networks with leakage delay and mixed time-varying delays
Sign Up to like & getrecommendations! Published in 2017 at "Neurocomputing"
DOI: 10.1016/j.neucom.2017.03.015
Abstract: This paper discusses the stability in Lagrange sense for complex-valued neural networks with time-varying discrete delays and distributed delays as well as leakage delay. By constructing an appropriate LyapunovKrasovskii functional, and employing free-weighting-matrix approach and… read more here.
Keywords: valued neural; neural networks; time varying; complex valued ... See more keywords
Global μ-synchronization of impulsive complex-valued neural networks with leakage delay and mixed time-varying delays
Sign Up to like & getrecommendations! Published in 2018 at "Neurocomputing"
DOI: 10.1016/j.neucom.2018.04.040
Abstract: Abstract In this paper, the problem on synchronization is investigated for a class of impulsive complex-valued neural networks with discrete and distributed time-varying delays as well as leakage delay. By constructing appropriate Lyapunov–Krasovskii functional, and… read more here.
Keywords: valued neural; neural networks; complex valued; impulsive complex ... See more keywords
Synchronization of two nonidentical complex-valued neural networks with leakage delay and time-varying delays
Sign Up to like & getrecommendations! Published in 2019 at "Neurocomputing"
DOI: 10.1016/j.neucom.2019.04.068
Abstract: Abstract This paper investigates the global asymptotical synchronization of two nonidentical complex-valued neural networks (CVNNs) with leakage delay and time-varying delays via integral sliding mode control approach. A suitable sliding surface and an appropriate Lyapunov–Krasovskii… read more here.
Keywords: synchronization two; valued neural; complex valued; synchronization ... See more keywords
Global exponential stability of delayed complex-valued neural networks with discontinuous activation functions
Sign Up to like & getrecommendations! Published in 2020 at "Neurocomputing"
DOI: 10.1016/j.neucom.2020.02.006
Abstract: Abstract This paper studies the global exponential stability of delayed complex-valued neural networks with discontinuous activation functions. By introducing the complex-valued Filippov differential inclusion, we construct the framework of studying the dynamical behaviors of complex-valued… read more here.
Keywords: valued neural; neural networks; activation functions; networks discontinuous ... See more keywords
An optical neural chip for implementing complex-valued neural network
Sign Up to like & getrecommendations! Published in 2021 at "Nature Communications"
DOI: 10.1038/s41467-020-20719-7
Abstract: Complex-valued neural networks have many advantages over their real-valued counterparts. Conventional digital electronic computing platforms are incapable of executing truly complex-valued representations and operations. In contrast, optical computing platforms that encode information in both phase… read more here.
Keywords: valued neural; neural networks; neural chip; complex valued ... See more keywords
The Performance Analysis of Complex-Valued Neural Network in Radio Signal Recognition
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3171856
Abstract: Many techniques have been developed for wireless signal recognition in many fifth generation (5G) enabled derivatives. Many harsh constraints, such as the large amount of model parameters and complex signal characteristics, drives intelligent recognition method… read more here.
Keywords: recognition; neural network; complex valued; valued neural ... See more keywords