Park Myoung Soo, Choi Jin Young
School of Electrical Engineering and Computer Science, Automation and Systems Research Institute, Seoul National University, Seoul 151-744, Korea.
IEEE Trans Syst Man Cybern B Cybern. 2009 Feb;39(1):254-67. doi: 10.1109/TSMCB.2008.2005483. Epub 2008 Dec 9.
In this paper, we present a neural network structure and a fast incremental learning algorithm using this network. The proposed network structure, named Evolving Logic Networks for Real-valued inputs (ELN-R), is a data structure for storing and using the knowledge. A distinctive feature of ELN-R is that the previously learned knowledge stored in ELN-R can be used as a kind of building block in constructing new knowledge. Using this feature, the proposed learning algorithm can enhance the stability and plasticity at the same time, and as a result, the fast incremental learning can be realized. The performance of the proposed scheme is shown by a theoretical analysis and an experimental study on two benchmark problems.
在本文中，我们提出了一种神经网络结构以及使用该网络的快速增量学习算法。所提出的网络结构名为实值输入的进化逻辑网络（ELN-R），是一种用于存储和使用知识的数据结构。ELN-R的一个显著特点是，存储在ELN-R中的先前学习到的知识可以用作构建新知识的一种构建块。利用这一特性，所提出的学习算法可以同时提高稳定性和可塑性，从而实现快速增量学习。通过对两个基准问题的理论分析和实验研究，展示了所提方案的性能。
