Giaquinto A, Fornarelli G
Dipartimento di Elettrotecnica ed Elettronica, Politecnicodi Bari, Bari 70125, Italy.
IEEE Trans Neural Netw. 2009 Nov;20(11):1837-41. doi: 10.1109/TNN.2009.2031870. Epub 2009 Sep 25.
In this brief, a synthesis procedure for cellular neural networks (CNNs) with space-invariant cloning templates is proposed. The design algorithm is based on the use of the evolutionary algorithm of the particle swarm optimization (PSO) with the application to associative memories. The proposed synthesis procedure takes into account requirements in terms of robustness to parametric variations. Numerical results show that the networks also guarantee good performances in terms of correct recall in the presence of noisy patterns.
在本简报中，提出了一种具有空间不变克隆模板的细胞神经网络（CNN）的合成过程。该设计算法基于粒子群优化（PSO）进化算法在关联记忆中的应用。所提出的合成过程考虑了对参数变化的鲁棒性要求。数值结果表明，在存在噪声模式的情况下，这些网络在正确召回方面也能保证良好的性能。
