Interacting Individually and Collectively Treated Neurons for Improved Visualization
Interacting Individually and Collectively Treated Neurons for Improved Visualization
复制标题
单独和集体处理的神经元相互作用以改善可视化
DOI：
10.1007/978-3-642-35638-4_18
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Ryotaro Kamimura
中科院分区：
文献类型：
--
作者：
上村龍太郎;上村龍太郎;上村龍太郎;上村龍太郎;上村龍太郎;上村龍太郎;上村龍太郎;Ryotaro Kamimura;Ryotaro Kamimura;Ryotaro Kamimura;Ryotaro Kamimura;Ryotaro Kamimura;Ryotaro Kamimura;Ryotaro Kamimura;Ryotaro Kamimura
在本文中，我们提出了一种新型的学习方法，其中神经元被单独和集体处理。此外，集体是根据神经元之间的距离和相似性来定义的。我们将该方法应用于自组织映射，因为我们的方法使得灵活控制神经元之间的合作过程成为可能。然后，我们将自组织映射的方法应用于英镑兑日元汇率的可视化。我们成功地产生了更清晰的阶级结构。整个汇率时期分为三个不同的时期。
In this paper, we propose a new type of learning method in which neurons are treated individually and collectively. In addition, the collectivity is defined in terms of distance and similarity between neurons. We applied the method to the self-organizing maps, because our method makes it possible to control flexibly a process of cooperation between neurons. Then, we applied the method with the self-organizing maps to the visualization of the pound-yen exchange rates. We succeeded in producing clearer class structure. The entire period of the exchange rates was divided into three distinct periods.