Novel distributed parameter neural networks are proposed for solving partial differential equations, and their dynamic performances are studied in Hilbert space. The locally connected neural networks are obtained by separating distributed parameter neural networks. Two simulations are also given. Both theoretical and practical results illustrate that the distributed parameter neural networks are effective and efficient for solving partial differential equation problems.
Hopfield J J, Tank D W. Biol. Cybern. 1985, 52(1): 141-152.[2]Kennedy M P, Chua L O. IEEE Trans. on CAS, 1988, GAS-35(3): 554-562.[3]Zhang S, Constantinids A G. IEEE Trans. on CAS, 1992, CAS-39(2): 441-452.[4]Wilson G, Powley G. Biol. Cybern. 1985, 58(1): 63-70.[5]Xu X, Tsai W T. Neural Networks, 1991, 4(1): 193-205.[6]Cichock A, Unbehauen R. IEEE Trans. on CAS, 1992, CAS-39(1): 124-128; CAS-39(5): 619-633.[7]Wang J. Electron. Lett. 1992, 28(10): 1751-1753.[8]Wang L W, Mendel J M. IEEE Trans. on Computer, 1991, C-40(6): 1337-1346.
DownLoad: