TY - JOUR
TI - A novel extended Li zeroing neural network for matrix inversion
AU - Gerontitis, D.
AU - Mo, C.
AU - Stanimirović, P.S.
AU - Tzekis, P.
AU - Katsikis, V.N.
JO - Neural Computing and Applications
PY - 2023
VL - 35
TODO - 19
SP - 14129-14152
PB - Springer Science and Business Media Deutschland GmbH
SN - null
TODO - 10.1007/s00521-023-08460-w
TODO - Activation analysis;  Inverse problems;  Matrix algebra;  Neural network models, Activation functions;  Extended sign-bi-power;  Finite convergence;  Li zeroing neural network;  Matrix inverse;  Matrix inversions;  Network-based;  Neural-networks;  Power;  Time varying, Chemical activation
TODO - An improved activation function, termed extended sign-bi-power (Esbp), is proposed. 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 problem. A detailed theoretical analysis confirms that the new activation function accomplishes fast convergence in calculating the time-varying matrix inversion. At the same time, illustrative numerical experiments substantiate the excellent performance of the proposed activation function over the Li and tunable activation functions. Convergence properties and numerical behaviors of the proposed ELi-ZNN model are examined. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.
ER -