学術雑誌論文 An Online Self-Constructive Normalized Gaussian Network with Localized Forgetting

Backhus, Jana  ,  Takigawa, Ichigaku  ,  Imai, Hideyuki  ,  Kudo, Mineichi  ,  Sugimoto, Masanori

E100 ( 3 )  , pp.865 - 876 , 2017-03 , 電子情報通信学会(The Institute of Electronics, Information and Communication Engineers / IEICE)
ISSN:1745-1337
内容記述
In this paper, we introduce a self-constructive Normalized Gaussian Network (NGnet) for online learning tasks. In online tasks, data samples are received sequentially, and domain knowledge is often limited. Then, we need to employ learning methods to the NGnet that possess robust performance and dynamically select an accurate model size. We revise a previously proposed localized forgetting approach for the NGnet and adapt some unit manipulation mechanisms to it for dynamic model selection. The mechanisms are improved for more robustness in negative interference prone environments, and a new merge manipulation is considered to deal with model redundancies. The effectiveness of the proposed method is compared with the previous localized forgetting approach and an established learning method for the NGnet. Several experiments are conducted for a function approximation and chaotic time series forecasting task. The proposed approach possesses robust and favorable performance in different learning situations over all testbeds.
本文を読む

http://eprints.lib.hokudai.ac.jp/dspace/bitstream/2115/65552/1/e100-a_3_865.pdf

このアイテムのアクセス数:  回

その他の情報