Agglomerative hierarchical clustering technique

Question

Earlier in the year, my AI lecturer taught us about agglomerative hierarchical clustering and K means clustering but his explanations are lost and i'm trying to figure out how he uses the data in the table below to create a dendogram. It would be great.

He comes up with the following table that outlines the similarities:

   Animal pairs          Similarities
Bear & Tiger                  4
Bear & Dog                    3
Bear & Giant Squid            2
Bear & Cat                    3
Tiger & Dog                   2
Tiger & Giant Squid           1
Tiger & Cat                   2
Dog & Giant Squid             2
Dog & Cat                     5
Giant Squid & Cat             2

And the resulting dendogram from the table above:

score 2 · Accepted Answer · answered May 11 '16 at 17:14

2

Always connect the most similar ones.

Dog and Cat are most similar, and are thus connected at level 5.

Bear and Tiger are connected at level 4.

etc.

answered May 11 '16 at 17:14

Has QUIT--Anony-Mousse

76,138
12
138
194

1

In addition to the answer, an article that explains an algorithm to build a [Hierarchical agglomerative clustering](http://nlp.stanford.edu/IR-book/html/htmledition/hierarchical-agglomerative-clustering-1.html) – Stéphane Eintrazi May 12 '16 at 07:12

Agglomerative hierarchical clustering technique

1 Answers1