For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
An Online Self-Constructive Normalized Gaussian Network with Localized Forgetting
Jana BACKHUS Ichigaku TAKIGAWA Hideyuki IMAI Mineichi KUDO Masanori SUGIMOTO
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2017/03/01
Online ISSN: 1745-1337
Type of Manuscript: PAPER
Category: Neural Networks and Bioengineering
Normalized Gaussian Networks, dynamic model selection, online learning, chaotic time series forecasting,
Full Text: PDF(1.3MB)
>>Buy this Article
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.