arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0705.0199cs.NEcs.AIcs.CV
收藏

无参数自组织映射算法

The Parameter-Less Self-Organizing Map algorithm

University of Queensland(昆士兰大学)

Erik Berglund, Joaquin Sitte

摘要:

无参数自组织映射(PLSOM)是在自组织映射(SOM)的基础上发展起来的一种新的神经网络算法。它消除了对学习率和用于学习率和邻域大小的退火方案的需要。我们讨论了PLSOM和SOM的相对性能,并演示了一些任务中,SOM失败,但PLSOM表现令人满意。最后,我们讨论了PLSOM的一些应用实例,并在一定的限制条件下给出了有序性的证明。

英文摘要:

The Parameter-Less Self-Organizing Map (PLSOM) is a new neural network algorithm based on the Self-Organizing Map (SOM). It eliminates the need for a learning rate and annealing schemes for learning rate and neighbourhood size. We discuss the relative performance of the PLSOM and the SOM and demonstrate some tasks in which the SOM fails but the PLSOM performs satisfactory. Finally we discuss some example applications of the PLSOM and present a proof of ordering under certain limited conditions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑