Scribd
Upload
22 views

Unsupervised Machine Learning

Unsupervised machine learning uses unlabeled input data to allow algorithms to group and analyze the data without guidance. There are two main types of clustering in unsupervised learning: hierarchical clustering and k-means clustering. Hierarchical clustering creates a tree structure by combining the most similar clusters together, while k-means clustering divides objects into k number of clusters where each object belongs to one cluster based on similarity. Euclidean distance is commonly used to calculate similarity between clusters in k-means.

Uploaded by

Soundarrajan OGP
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
22 views

Unsupervised Machine Learning

Unsupervised machine learning uses unlabeled input data to allow algorithms to group and analyze the data without guidance. There are two main types of clustering in unsupervised learning: hierarchical clustering and k-means clustering. Hierarchical clustering creates a tree structure by combining the most similar clusters together, while k-means clustering divides objects into k number of clusters where each object belongs to one cluster based on similarity. Euclidean distance is commonly used to calculate similarity between clusters in k-means.

Uploaded by

Soundarrajan OGP
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 20

Unsupervised Machine

learning
Anand R
Unsupervised ML

• In unsupervised
learning, machine
learning model uses
unlabeled input data
and allows the
algorithm to act on
that information
without guidance.
Clustering?
• In machine learning, clustering is used for analyzing and grouping data
which does not include pre-labeled class or even a class attribute at all.
Types of Clustering
Hierarchical Clustering

• In Hierarchical clustering,
clusters have a tree like
structure or a parent child
relationship. Here, the two
most similar clusters are
combined together and
continue to combine until all
objects are in the same
cluster.
K Means

• K- means is a collection
of objects which are
“similar” between them
and are “dissimilar” to the
objects belonging to other
clusters. It is a division of
objects into clusters such
that each object is in
exactly one cluster, not
several.
Flow Chart for K-
Means Clustering
Euclidian Distance

•
Applying K – Means Clustering with
two clusters

S.No X Y
1 1 1
2 1.5 2
3 3 4
4 5 7
5 3.5 5
6 4.5 5
7 3.5 4.5
Initial Assume any two cluster as reference

S.No X Y
C1 1 1
C2 5 7
Euclidian Distance calculation
•
S.No X Y
C1 1 1
C1 1.5 2
Mean

Now C1 Becomes 1.25 1.5

Calculate Mean
Euclidian Distance calculation
•
S.No X Y
C1 1 1
C1 1.5 2
C1 3 4
Mean

Now C1 Becomes 1.8 2.3


Calculate Mean
Euclidian Distance calculation
•
S.No X Y
C2 5 7
C2 3.5 5
Mean

Now C2 Becomes 4.25 6

Calculate Mean
Euclidian Distance calculation
•
S.No X Y
C2 5 7
C2 3.5 5
C2 4.5 5
Mean

Now C1 Becomes 4.3 5.6


Calculate Mean
Euclidian Distance calculation
•
Hierarchical agglomerative clustering
Need to define a distance d(P,Q) between groups, given a distance measure d(x,y)
between observations.

Commonly used distance measures:

1. d1(P,Q) = min d(x,y), for x in P, y in Q ( single linkage )

2. d2(P,Q) = ave d(x,y), for x in P, y in Q ( average linkage )

3. d3(P,Q)
d 4 ( P=, Q
max
)  d(x,y),
x P  x Qfor x in P, y in Q ( complete linkage )

P Q
4. ( centroid method )
2
d5 ( P , Q )  2 xP  xQ
P  Q

5. d5 is called Ward’s distance. ( Ward’s method )

You might also like