Growing Greedy Search and its Application to Hysteresis Neural Networks
Growing Greedy Search and its Application to Hysteresis Neural Networks
复制标题
增长贪婪搜索及其在滞后神经网络中的应用
DOI：
10.1007/978-3-319-26555-1_36
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
K. Yamaoka and T. Saito
中科院分区：
文献类型：
--
作者：
Sasaki Hikaru;Horiuchi Tadashi;Kato Satoru;岩田悠,梁宏博,上田直哉,田野,朱赤,吉岡将孝;K. Yamaoka and T. Saito
提出了一种增长贪婪搜索算法及其在迟滞神经网络联想记忆中的应用。在该算法中，个体与交叉连接参数相对应，代价函数评估虚假记忆的数量，个体集可以根据全局最优值增长。通过基本的数值实验，研究了该算法的有效性。
This paper presents the growing greedy search algorithm and its application to associative memories of hysteresis neural networks in which storage of desired memories are guaranteed. In the algorithm, individuals correspond to cross-connection parameters, the cost function evaluates the number of spurious memories, and the set of individuals can grow depending on the global best. Performing basic numerical experiments, the algorithm efficiency is investigated.