No self-introduction
Loading
Profile
Follow
codes (1)
Kmeans cluster
no vote
This is a project in natural language process, it is one of classic clustering algorithms in data mining,the algorithms based on
distance,First choose k objects from n arbitrary data objects as the initial clustering center; for the left objects, according to
their similarity with the clustering center (distance), assign them respectively with its most similar clustering center
(represent) clustering; Then to calculate each received new clustering center of the cluster (average of all the objects in
the cluster). Repeat this process until the standard measurement function began to convergence. Generally USES the
chenglan 2016-08-23
chenglan 0 0
1
No more~
Follows0
Fans0