Mar 22, 2023 · A novel improved zeroing neural network, termed ELi-ZNN dynamics, initiated by a novel activation function—called extended sign-bi-power (Esbp)— ...
A detailed theoretical analysis confirms that the new activation function accomplishes fast convergence in calculating the time-varying matrix inversion ...
An extension of the Li zeroing neural network (ELi-ZNN) based on the Esbp activation is derived to obtain the online solution of the time-varying inversion ...
A family of zeroing neural networks based on new nonlinear activation functions is proposed for solving various time-varying linear matrix equations (TVLME).
This paper investigates the problem of computing the time-varying {2,3}- and {2,4}-inverses through the zeroing neural network (ZNN) method, which is presently ...
A novel extended Li zeroing neural network for matrix inversion. https://doi.org/10.1007/s00521-023-08460-w ·. Journal: Neural Computing and Applications ...
A novel extended Li zeroing neural network for matrix inversion. Dimitrios Gerontitis, Changxin Mo, Predrag S. Stanimirović, P. Tzekis, Vasilios N. Katsikis.
Jan 16, 2023 · The newly proposed DIEZNN model can guarantee a normal solution to the time-varying quadratic matrix equation task no matter how much linear noise there is.
A new hybrid Zhang neural network (HZNN) model is formulated to solve time-varying matrix inversion problem.
Missing: extended | Show results with:extended
A novel extended Li zeroing neural network for matrix inversion. D Gerontitis, C Mo, PS Stanimirović, P Tzekis, VN Katsikis. Neural Computing and Applications ...