Name
Title | ||
|---|---|---|
Reducing Redundancy With Unit Merging For Self-Constructive Normalized Gaussian Networks |
Abstract | ||
|---|---|---|
In this paper, a Normalized Gaussian Network (NGnet) is introduced for online sequential learning that uses unit manipulation mechanisms to build the network model self-constructively. Several unit manipulation mechanisms have been proposed for online learning of an NGnet. However, unit redundancy still exists in the network model. We propose a merge mechanism for such redundant units, and change its overlap calculation in order to improve the identification accuracy of redundant units. The effectiveness of the proposed approach is demonstrated in a function approximation task with balanced and imbalanced data distributions. It succeeded in reducing the model complexity around 11% on average while keeping or even improving learning performance. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1007/978-3-319-44778-0_52 | ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT I |
Keywords | Field | DocType |
Normalized Gaussian Networks, Self-constructive model adaptation, Redundancy reduction | Normalization (statistics),Pattern recognition,Function approximation,Constructive,Computer science,Gaussian,Redundancy (engineering),Artificial intelligence,Merge (version control),Machine learning,Network model,Model complexity | Conference |
Volume | ISSN | Citations |
9886 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 8 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jana Backhus | 1 | 0 | 1.01 |
| Ichigaku Takigawa | 2 | 209 | 18.15 |
| Hideyuki Imai | 3 | 103 | 25.08 |
| Mineichi Kudo | 4 | 927 | 116.09 |
| Masanori Sugimoto | 5 | 775 | 95.39 |