Introduction to

Machine
Learning
Name: Sk Samiul Islam
Roll No: ECE204034
Subcode: ECEUGPR01

Supervised by- Dr. Md. Abdul Alim Sheikh

Introduction
Contents
 What is Machine Learning
 Why Machine Learning
 Types of Machine Learning Model
 Supervised Learning
 Unsupervised Learning
 Reinforcement Learning
 Application of Machine Learning
 Conclusion
 Resources

3
What is Machine Learning?
 Machine learning is a type of artificial intelligence that allows
software applications to become more accurate at predicting
outcomes without being explicitly programmed to do so.
 Machine learning enables a machine to automatically learn from data,
improve performance from experiences, and predict things without
being explicitly programmed.
 Machine learning algorithms use historical data as input to predict
new output values.

i/p i/p
code o/p
o/p ML code Comp

4
Why Machine Learning?
 Machine learning is important because it gives enterprises a
view of trends in customer behavior and business operational
patterns, as well as supports the development of new products.
 Learning is used when:
 Human expertise does not exist (navigating on Mars),
 Humans are unable to explain their expertise (speech recognition)
 Solution changes in time (routing on a computer network)
 Solution needs to be adapted to particular cases (user biometrics)

5
Types of Machine Learning Model
 Supervised Learning
 Classification(Discrete labels)
 Regression(Real value)
 Unsupervised Learning
 Semi-supervised Learning
 Reinforcement Learning

6
Supervised Learning
 Supervised learning is the types of machine learning in which
machines are trained using well "labelled" training data, and on
basis of that data, machines predict the output. The labelled data
means some input data is already tagged with the correct output.

 How it work
 In supervised learning, models
are trained using labelled dataset,
where the model learns about each
type of data. Once the training
process is completed, the model
is tested on the basis of test data
& then it predicts the output.

7
Training & Testing Model
 Training is the process of the making the system able to learn.

8
Types of Supervised Learning
 Regression
 Regression algorithms are used if there is a relationship between the input
variable and the output variable. It is used for the prediction of continuous
variables, such as Weather forecasting, Market Trends, etc.
 Classification
 Classification algorithms are used when the output variable is categorical,
which means there are two classes such as Yes-No, Male-Female, True-
false, etc.

Regression Classification

• Linear Regression • Random Forest

• Regression Trees • Decision Trees
• Non-Linear Regression • Logistic Regression
• Polynomial Regression • Support vector Machines

9
Supervised Learning: Uses
 Prediction of future cases: Use the rule to predict the output
for future inputs
 Knowledge extraction: The rule is easy to understand
 Compression: The rule is simpler than the data it explains
 Outlier detection: Exceptions that are not covered by the rule,
e.g., fraud

10
Unsupervised Learning
 Unsupervised learning is a type of machine learning in which
models are trained using unlabeled dataset and are allowed to act
on that data without any supervision.
 How it work
 Unsupervised ML algorithms
do not require data to be labeled.
They sift through unlabeled data
to look for patterns that can be
used to group data points into
subsets. Most types of deep
learning, including neural
networks, are unsupervised
algorithms.

11
Types of Unsupervised Learning
 Clustering
 Splitting the dataset into groups based on similarity.
 Association mining
 Identifying sets of items in a data set that frequently occur together.

 Unsupervised Learning algorithms

 K-means clustering
 KNN (k-nearest neighbors)
 Hierarchal clustering
 Anomaly detection
 Neural Networks
 Principle Component Analysis
 Independent Component Analysis

12
Reinforcement Learning
 Reinforcement Learning is a feedback-based Machine learning
technique in which an agent learns to behave in an environment by
performing the actions and seeing the results of actions. For each good
action, the agent gets positive feedback, and for each bad action, the
agent gets negative feedback or penalty.
 How it work
 Reinforcement learning work
by programming an algorithm
with a distinct goal and a prescribed
set of rules for accomplishing that
goal.This algorithm received positive
rewards when that action goes to
the ultimate goal & avoid punishment
when it goes to the farther away from
the ultimate goal.

13
Reinforcement Learning Example
 Robotics
 Robots can learn to perform tasks the physical world using this technique.
 Video gameplay
 Reinforcement learning has been used to teach bots to play a number of video
games.
 Resource management
 Given finite resources and a defined goal, reinforcement learning can help
enterprises plan out how to allocate resources.

14
Application of Machine Learning

15
Conclusion
 We have a simple overview of some technique and algorithms
in machine learning. Furthermore,there are more and more
techniques apply in machine learning as a solution. In the
future,machine learning will play as important role in our
daily life.

16
Resources: Datasets
 UCI Repository:
https://archive.ics.uci.edu/ml/datasets.php
 Kaggle:
https://www.kaggle.com/datasets
 Google Dataset:
https://datasetsearch.research.google.com/

17
Resources & Journals
 Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical
learning: Data mining, inference, and prediction. Springer.
 Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An
introduction. MIT Press.

 https://developers.google.com/machine-learning/crash-course/
 https://scikit-learn.org/

18
Thank Sk Samiul Islam

You
sksamiul602@gmail.com