摘要
本文利用ＴＨ神经网络求解特征抽样和过抽样情况下的周期（或有限）的离散信号的Ｇａｂｏｒ展开系数．理论分析和模拟实验表明，这种神经网络可以在电路时常数数量级给出与准确解任意接近的解，而且不存在编程复杂性问题．
In this paper, it is proposed that the Gabor expansion coefficients of a period(or finite)discretesignal in both the critical sampling case and the oversampling case can be computed by TH neural networks.Theoretical analysis and simulations show that this network will certainly provide approximate solutions arbitrarilyclose to the accurate one within the time of the order of time constants of this network without any programmingcomplexity.
出处
《电子学报》
EI
CAS
CSCD
北大核心
1997年第10期48-51,共4页
Acta Electronica Sinica
