please re-write this answer by keyboard don't use handwriting
Answer 1)
k-mean clustering is cluster of items with the same target
category are identified and predicitions for new data items aremade
by assuming that type are of the same type as the nearest cluster
center.
Implementation
1>place k points into the space represented by the objects that
are bing clustered.
2>assign each object to the group that has closest
centroid.
3>when all objects have been assigned,recalculate the positions
of the k centroids
4>repreat step 2 & 3 until the centroids no longer move
>The image explains the algo works in the cas when k=2.we randomly select the values for μ1 and μ2 and the algorithm converges when the mems no longer change (let μi=mi)
>the result depends a lot on the value of k i.e the an actual
number of clusters often we have no way of knowing how man clusters
exists.
>below picture shows or figure shows what happens when we use
k=3(let μi=mi)
sometimes the clustering division turns out to be better at highest
k.
>we can go all the way upto k=n , this proceduce will give us
someting know as the nearest
neighbour classifies
>it perform great of the number of feature vector is
large,however,computatonally it is much more expresive.
The Sa me ct ary areId dh a t min as the nearest cluster center Placek Paint into Ma group-that-h...