Expected Quantization Error Stability-Based Self-Organizing Growth Neural Network With Adaptive Output Network Scale

Expected Quantization Error Stability-Based Self-Organizing Growth Neural Network With Adaptive Output Network Scale

Self-organizing growth neural network (SOGNN) is an unsupervised clustering algorithm based on competitive learning, which can extract the distribution information and topology information of input data. However, the current SOGNN lacks effective and stable judgment indicators for the scale of netwo...

Full description

Bibliographic Details
Main Authors: Chaoliang Zhong, Yao Zhou
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Growing neural gas
self-organization neural network
unsupervised learning
competitive learning
Online Access:https://ieeexplore.ieee.org/document/8836505/

Internet

https://ieeexplore.ieee.org/document/8836505/

Similar Items