摘要
This article mainly studies the multistability of complex-valued neural networks (CVNNs) with general periodic-type activation functions. In order to improve the storage capacity of associative memory, a general periodic-type activation function is introduced which obtains three different numbers of equilibrium points (EPs), including unique, finite, and countable infinite. The existence and stability of equilibria are investigated based on Brouwer's fixed point theorem and M-matrix method. By means of a sign function on complex numbers, stability is confirmed using a new norm on the absolute values of the real and imaginary parts. The attraction basins of exponentially stable equilibria are estimated, which are bigger than the subspaces of the original division. Also, the design of associative memory is given. Finally, two numerical simulation examples verify the obtained results.
学科与关键词
- Analysis and Design of Multivalued High-Capacity Associative Memories Based on Delayed Recurrent Neural NetworksZhang, Jiahui; Zhu, Song*; Bao, Gang; Liu, Xiaoyang; Wen, ShipingIEEE Transactions on Cybernetics, 2022, 52(12): 12989-13000.被引 9
- Multistability of Dynamic Memristor Delayed Cellular Neural Networks With Application to Associative MemoriesDeng, Kun; Zhu, Song*; Bao, Gang; Fu, Jun; Zeng, ZhigangIEEE Transactions on Neural Networks and Learning Systems, 2023, 34(2): 690-702.被引 20
- Multistability of Fuzzy Neural Networks With a General Class of Activation Functions and State-Dependent Switching RulesOu, Shiqin; Guo, Zhenyuan; Wang, Jun*IEEE Transactions on Fuzzy Systems, 2023, 31(2): 645-659.被引 2
