Dynamic Comptitive Learning Techniques for Knowledge Representation
Shang Gang · Microcomputer Development · 1997
The competitive learning techniques is a well known algorithm used in neural networks which classifies the input vectors. Dynamic competitive learning is an unsuperised learning technique, which consists of two additional parts related to conventional competitive learning: a method of generation of new units within a cluster and a method of generating new clusters. The model is capable for the storage of complex data structures.