论文部分内容阅读
本文提出一个实时奇异值分解(SVD)的全并行神经网络,给出并证明了它的有界性定理和稳定性定理,同时给出一个模拟例子。理论和模拟结果都说明所提出的神经网络对于SVD是有效的。
In this paper, an all-parallel neural network for real-time singular value decomposition (SVD) is proposed, its boundedness theorem and stability theorem are given and proved, and a simulation example is given. Both theoretical and simulation results show that the proposed neural network is effective for SVD.