On-line learning of sequence data based on Self-Organizing Incremental Neural Network
On-line learning of sequence data based on Self-Organizing Incremental Neural Network
复制标题
基于自组织增量神经网络的序列数据在线学习
DOI：
10.1109/ijcnn.2008.4634351
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
O. Hasegawa
中科院分区：
文献类型：
--
作者：
S. Okada;O. Hasegawa
This paper presents an on-line, continuously learning mechanism for sequence data. The proposed approach is based on SOINN-DTW method (Okada and Hasegawa, 2007), which is designed for learning of sequence data. It is based on self-organizing incremental neural network (SOINN) and dynamic time warping (DTW). Using SOINNpsilas function represents the topological structure of online input data, the output distribution of each states is represented and adapted in a self-organizing manner corresponding to online input data. Consequently, this method can train a network and estimate parameters of the output distribution using new (on-line) data continuously, based on scarce batch-training data. Through online learning, the recognition accuracy is improved continuously. To confirm the effectiveness of the on-line learning mechanism of SOINN-DTW, we present an extensive set of experiments that demonstrate how our method outperforms the online learning method of HMM in classifying phoneme data.
影响因子：
4.3
作者：
LEGGETTER, CJ;WOODLAND, PC
通讯作者：
WOODLAND, PC