This paper is devoted to the problem of stabilizing a Hopfield-type neural network with bi-directional ring architecture and two delays. The delay-independent and delay-dependent stability conditions are explicitly pr...This paper is devoted to the problem of stabilizing a Hopfield-type neural network with bi-directional ring architecture and two delays. The delay-independent and delay-dependent stability conditions are explicitly presented by the method of the characteristic roots and the skill of mathematical analysis. Moreover, if a link between the adjacent two neurons is cut, the ring neural network turns to a linear one, and the stability results are also established. Furthermore, a comparative analysis for the ring and linear network shows that the stability domain is enlarged after the breaking.展开更多
In this study a neural network approach is proposed to realize an automatic numerical prediction of the interfacial friction factor and the flow stress of materials. Decrease in the inner diameter and reduction in the...In this study a neural network approach is proposed to realize an automatic numerical prediction of the interfacial friction factor and the flow stress of materials. Decrease in the inner diameter and reduction in the height of the ring are taken as input展开更多
Based on the implementation of NNSPC (Neural NetWork Synchronous Parallel Computer) developed by NJU, this paper discusses two schemes for implementing artificial neural network computer withdistributed memories: One ...Based on the implementation of NNSPC (Neural NetWork Synchronous Parallel Computer) developed by NJU, this paper discusses two schemes for implementing artificial neural network computer withdistributed memories: One is Switch Network Structure; the other is Ring Topology Structure. This papergives a comparison betWeen the two schemes and the principles of scheme selection.展开更多
文摘This paper is devoted to the problem of stabilizing a Hopfield-type neural network with bi-directional ring architecture and two delays. The delay-independent and delay-dependent stability conditions are explicitly presented by the method of the characteristic roots and the skill of mathematical analysis. Moreover, if a link between the adjacent two neurons is cut, the ring neural network turns to a linear one, and the stability results are also established. Furthermore, a comparative analysis for the ring and linear network shows that the stability domain is enlarged after the breaking.
文摘In this study a neural network approach is proposed to realize an automatic numerical prediction of the interfacial friction factor and the flow stress of materials. Decrease in the inner diameter and reduction in the height of the ring are taken as input
文摘Based on the implementation of NNSPC (Neural NetWork Synchronous Parallel Computer) developed by NJU, this paper discusses two schemes for implementing artificial neural network computer withdistributed memories: One is Switch Network Structure; the other is Ring Topology Structure. This papergives a comparison betWeen the two schemes and the principles of scheme selection.
