The last step in training phase is refinement of the Clusters
found above. Although DynamicClustering counters all the
basic k-means disadvantages, setting the intra-Cluster similarity
r may require experimentation. Also, a Cluster may
have a lot in common with another, i.e., sequences assigned
to it are as close to it as they are to another Cluster. There
may also be denser sub-Clusters within the larger ones.
標簽:
DynamicClusteri
refinement
Although
Clusters
上傳時間:
2014-01-04
上傳用戶:watch100