Title :
A synthesis procedure for a generalized neural network
Author :
Yan, Yan ; Li, Jie Gu
Author_Institution :
Inst. of Image Process & Pattern Recognition, Shanghai Jiao Tong Univ., China
Abstract :
An FTTB (from top to bottom) design strategy for a neural network is introduced. From the scheme the authors present a design method and construct a generalized neural network which has some good qualitative behavior, e.g. any number of isolated prototypes can be set to asymptotically stable fixpoints, and any track converges to one of the equilibria. The time/space complexity of the model is O(mn ), as opposed to O(nn) of Hopfield-like models. A simulation experiment shows its good recognition ability
Keywords :
Hopfield neural nets; computational complexity; generalisation (artificial intelligence); Hopfield-like models; asymptotically stable fixpoints; generalized neural network; isolated prototypes; qualitative behavior; space complexity; time complexity; Biological neural networks; Brain modeling; Circuits; Costs; Nervous system; Network synthesis; Neural networks; Neurons; Power system modeling; Prototypes;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.287177
