Overview

1
Introduction
• machine learning technique in which the users do not
need to supervise the model
• allows the model to work on its own to discover patterns
and information that was previously undetected
• mainly deals with the unlabeled data

2
Unsupervised Learning Overview

unlabeled fit structur

data (no e
answers)

new predict map

unlabeled + model new
data data to
structur
e
Introduction
• Why unsupervised learning?
• finds all kind of unknown patterns in data.
• find features which can be useful for categorization.
• can taken place in real time, so all the input data to
be analyzed and labeled in the presence of learners.
• easier to get unlabeled data from a computer than
labeled data, which needs manual intervention.

4
Types of Unsupervised Learning Algorithms
• Clustering
• finding a structure or pattern in a collection of uncategorized data
• process data and find natural clusters(groups) if they exist in the data
• types: Exclusive (partitioning), Agglomerative, Overlapping, Probabilistic
• Dimension reduction
• dimension reduction technique that finds the variance maximizing
directions onto which to project the data
• use structural characteristics to simplify data
• Association
• rule learning problem to establish associations amongst data objects inside
large databases
• For example, people that buy a new home most likely to buy new furniture

5
Some of the Unsupervised Learning Algorithms
• Clustering
• K-means - data points are assigned into K groups, where K represents the number of
clusters based on the distance from each group’s centroid
• Hierarchical clustering, also known as hierarchical cluster analysis (HCA) - categorized in
two ways; they can be agglomerative or divisive
• probabilistic model - helps us solve density estimation or “soft” clustering problems where
data points are clustered based on the likelihood that they belong to a particular
distribution
• Dimension reduction
• Principal component analysis (PCA) - to reduce redundancies and to compress datasets
through feature extraction
• Singular value decomposition (SVD) - factorizes a matrix, A, into three, low-rank matrices
• Autoencoders leverage neural networks to compress data and then recreate a new
representation of the original data’s input
• Association
• Apriori algorithms – for market basket analyses, leading to different recommendation
engines for music platforms and online retailers
6
Types of Unsupervised Learning

Clustering identify unknown structure in data

Dimensionali
use structural characteristics to simplify
ty Reduction
data
Clustering: Finding Distinct Groups

text articles fit

of unknown + mode model
topics l

text articles predict

mode predict
of unknown + l
similar
topics
articles
Application of Clustering
• Recommendation engines
• Market segmentation
• Social network analysis
• Search result grouping
• Medical imaging
• Image segmentation
• Anomaly detection
9
Dimensionality Reduction: Simplifying
Structure
high fit
resolution + mode model
images l

high predict
mode compressed
resolution + l
images
images
Applications of Unsupervised Machine
Learning
• Clustering automatically split the dataset into groups base on
their similarities
• Anomaly detection can discover unusual data points in your
dataset. It is useful for finding fraudulent transactions
• Association mining identifies sets of items which often occur
together in your dataset
• Latent variable models are widely used for data
preprocessing. Like reducing the number of features in a
dataset or decomposing the dataset into multiple
components

11
Disadvantages of Unsupervised
Learning
• cannot get precise information regarding data sorting, and the output
as data used in unsupervised learning is labeled and not known
• less accuracy of the results is because the input data is not known
and not labeled by people in advance. This means that the machine
requires to do this itself.
• the spectral classes do not always correspond to informational
classes.
• the user needs to spend time interpreting and label the classes which
follow that classification.
• spectral properties of classes can also change over time so you can't
have the same class information while moving from one image to
another.
12
Pre-processing and Scaling
• data preprocessing and normalization become very
important when it comes to the implementation of different
Machine Learning Algorithms
• can affect the outcome of the learning model significantly, it
is very important that all features are on the same scale

13
Types of pre-processing and scaling
• StandardScaler
• ensures that for each feature in the dataset mean is 0 and variance is 1 and brings
all features to the same magnitude
• doesn’t ensure any minimum and maximum values for the features
• RobustScaler
• similar to StandardScaler but uses the median and quartiles instead of mean and
variance
• makes scaler ignore data points that are very different from the rest (measurement
errors)
• Normalizer scales
• each data point such that the feature vector has a Euclidian length of 1
• Every data point is scaled by a different number (by the inverse of its length)
• used when the only direction of the data matters, not the length of the feature
vector
• MinMaxScaler
• transforms all the input variables, so they’re all on the same scale between zero and
one
• computes the minimum and maximum values for each feature on the training data,
and then applies the min - max transformation for each feature.

Source: https://levelup.gitconnected.com/importance-of-data-
preprocessing-and-scaling-in-machine-learning-21db1d4377ec 14
Types of pre-processing and scaling

Source: https://levelup.gitconnected.com/importance-of-data-preprocessing-and-scaling-
15
in-machine-learning-21db1d4377ec
Reference:
• https://www.guru99.com/unsupervised-machine-learning.html
• https://stanford.edu/~shervine/teaching/cs-229/cheatsheet-
unsupervised-learning#dimension-reduction
• https://www.ibm.com/cloud/learn/unsupervised-learning
• https://levelup.gitconnected.com/importance-of-data-
preprocessing-and-scaling-in-machine-learning-21db1d4377ec
• https://www.analyticsvidhya.com/blog/2016/11/an-introduction-
to-clustering-and-different-methods-of-clustering/
• https://www.digitalvidya.com/blog/the-top-5-clustering-
algorithms-data-scientists-should-know/

16