LEADER 04297nam  22007335  450 
001 9911049085303321
005 20260102120547.0
010   $a3-032-01493-X
024 7 $a10.1007/978-3-032-01493-1
035   $a(CKB)44769993400041
035   $a(MiAaPQ)EBC32484366
035   $a(Au-PeEL)EBL32484366
035   $a(DE-He213)978-3-032-01493-1
035   $a(EXLCZ)9944769993400041
100   $a20260102d2025      u|         0
101 0 $aeng
135   $aur|||||||||||
181   $ctxt$2rdacontent
182   $cc$2rdamedia
183   $acr$2rdacarrier
200 10$aGeneralized Matrix Inversion: A Machine Learning Approach /$fby Predrag S. Stanimirovi?, Yimin Wei, Shuai Li, Dimitrios Gerontitis, Xinwei Cao
205   $a1st ed. 2025.
210  1$aCham :$cSpringer Nature Switzerland :$cImprint: Springer,$d2025.
215   $a1 online resource (492 pages)
225 1 $aArtificial Intelligence (R0) Series
311 08$a3-032-01492-1 
327   $a1. Background Information -- 2 Gradient Neural Network (GNN) and their Modifications -- 3 Zeroing Neural Network (ZNN) -- 4 From iterations to ZNNs and vice versa, 5 Modified ZNN dynamical systems.
330   $aThis book presents a comprehensive exploration of the dynamical system approach in numerical linear algebra, with a special focus on computing generalized inverses, solving systems of linear equations, and addressing linear matrix equations. Bridging four major scientific domains?numerical linear algebra, recurrent neural networks (RNNs), dynamical systems, and unconstrained nonlinear optimization?this book offers a unique, interdisciplinary perspective. Generalized Matrix Inversion: A Machine Learning Approach explores the theory and application of recurrent neural networks, particularly continuous-time recurrent neural networks (CTRNNs), which use systems of ordinary differential equations to model the influence of inputs on neurons. Special attention is given to CTRNNs designed for finding zeros of equations or minimizing nonlinear functions, with detailed coverage of two important classes: Gradient Neural Networks (GNN) and Zhang (Zeroing) Neural Networks (ZNN). Both time-varying and time-invariant models are examined across scalar, vector, and matrix cases. Based on the authors? research that has been published in leading scientific journals, the book spans a variety of disciplines, including linear and multilinear algebra, generalized inverses, recurrent neural networks, dynamical systems, time-varying problem solving, and unconstrained nonlinear optimization. Readers will find a global overview of activation functions, rigorous convergence analysis, and innovative improvements in the definition of error functions for GNN and ZNN dynamic systems. Generalized Matrix Inversion: A Machine Learning Approach is an essential resource for researchers and practitioners seeking advanced methods at the intersection of machine learning, optimization, and matrix computation.
410  0$aArtificial Intelligence (R0) Series
606   $aMachine learning
606   $aDynamics
606   $aNonlinear theories
606   $aAlgebras, Linear
606   $aDynamics
606   $aAlgorithms
606   $aMathematics$xData processing
606   $aMachine Learning
606   $aApplied Dynamical Systems
606   $aLinear Algebra
606   $aDynamical Systems
606   $aDesign and Analysis of Algorithms
606   $aComputational Mathematics and Numerical Analysis
615  0$aMachine learning.
615  0$aDynamics.
615  0$aNonlinear theories.
615  0$aAlgebras, Linear.
615  0$aDynamics.
615  0$aAlgorithms.
615  0$aMathematics$xData processing.
615 14$aMachine Learning.
615 24$aApplied Dynamical Systems.
615 24$aLinear Algebra.
615 24$aDynamical Systems.
615 24$aDesign and Analysis of Algorithms.
615 24$aComputational Mathematics and Numerical Analysis.
676   $a006.31
700   $aStanimirovi?$b Predrag S$01380215
801  0$bMiAaPQ
801  1$bMiAaPQ
801  2$bMiAaPQ
906   $aBOOK
912   $a9911049085303321
996   $aGeneralized Matrix Inversion: A Machine Learning Approach$94534547
997   $aUNINA