Department of CE

Unit no : 1
Introduction to
Machine Learning
(3170724)

Prof. Hetvy Jadeja

 Department of CE

ML: Machine Learning Unit no : 1

Introduction to Introduction to
Machine Learning

Machine Learning (3170724)

Prof. Hetvy Jadeja

Outline :
Introduction Department of CE

Evaluation of Machine Learning

Unit no : 1
What is Human Learning?
Introduction to
Types of Human Learning Machine Learning
What is Machine Learning? (3170724)

Types of Machine Learning

When not to use ML?
Application of ML
Tools for Machine Learning Prof. Hetvy Jadeja
 • ML is an interdisciplinary field:
Data Analyst: visualize, analyze data,
optimization
Data Engineers: build and test
scalable/stable/optimal ecosystems for data
scientists to run their algorithms
Introduction Database Administrator: responsible for the
proper functioning of all the databases
Data Scientist: perform predictive analysis and
offer actionable insights
Statistician: extract and offer valuable insights
from the data using statistical theory and tools
Evaluation of
Machine
Learning
Evaluation of
Machine
Learning
 • In cognitive science, learning is typically referred to
as the process of gaining information through
observation.
• A task can be as simple as walking down the street
or doing the homework; or as complex as deciding
What is the angle in which a rocket should be launched so
that it can have a particular trajectory.
Human
• Why do we need to learn?
Learning? • With more knowledge, the ability to do homework
with less number of mistakes increases
• Thus, With more learning, tasks can be performed
more efficiently.
 1. Learning under expert guidance
 Somebody who is an expert in the subject directly
teaches us.
 The process of gaining information from a person
having sufficient knowledge due to past experience.
(e.g. learning of child)
Types of 2. Learning guided by knowledge gained from experts
 we build our own notion indirectly based on what we
Human have learnt from the expert in the past
Learning  learning also happens with the knowledge which has
been imparted by teacher or mentor at some point of
time in some other form
 E.g. a kid can select one odd word from a set of words
because it is a verb and other words being all nouns,
due to English learned in school
 3. Learning by self
 we do it ourselves, may be after multiple attempts,
some being unsuccessful
 Learning from our mistakes in past
 E.g. Child learning to walk through obstacles
Types of
Human
Learning
 • “Machine learning is the field of study that gives
computers the ability to learn without being
explicitly programmed”
- Arthur Samuel, AI pioneer, 1959
• “A computer program is said to learn from
experience E with respect to some class of tasks
What is T and performance measure P, if its performance
Machine at tasks in T, as measured by P, improves with
experience E”
Learning? - Tom Mitchell, ML Professor at CMU
• Algorithms that
• improve their performance (P)
• at some task (T)
• with experience (E)
Traditional v/s
Machine
Learning
 • Data Input: Past data or information is utilized as a
basis for future decision-making
• Abstraction: The input data is represented in a
broader way through the underlying algorithm
• Generalization: The abstracted representation is
How do generalized to form a framework for making
machine decisions
learn?
 • For defining a new problem, which can be solved
using ML, a simple framework can be used. The
framework involves answering three questions:

1. What is the problem?

 Describe the problem informally and formally and list
Well- posed assumptions and similar problems.
learning 2. Why does the problem need to be solved?
problem  List the motivation for solving the problem, the
benefits that the solution will provide and how the
solution will be used.

3. How would I solve the problem?

 Describe how the problem would be solved manually
to flush domain knowledge.
Types of
Machine
Learning
 1. Supervised learning
 Also called predictive learning
 Predict the class of unknown objects based on prior
class-related information of similar objects.
2. Unsupervised learning
Types of  Also called descriptive learning
Machine  Find patterns in unknown objects by grouping
similar objects together.
Learning 3. Reinforcement learning
 Learn to act on its own to achieve the given goals.
  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
Supervised already tagged with the correct output.
Learning
Supervised
Learning
 Classification Regression

Types of
Supervised
Learning
  Unsupervised learning is a machine learning
technique in which models are not
supervised using training dataset. Instead,
models itself find the hidden patterns and
insights from the given data. It can be
Unsupervised compared to learning which takes place in the
human brain while learning new things.
Learning
 Association
Clustering Analysis

Types of
Unsupervised
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
Reinforce- penalty.
ment
Learning
Comparison –
Supervised,
Unsupervised
and
Reinforcemen
t Learning
Comparison –
Supervised,
Unsupervised
and
Reinforcemen
t Learning
Comparison –
Supervised,
Unsupervised
and
Reinforcemen
t Learning
 • Machine learning should not be applied to tasks in
which humans are very effective or frequent human
intervention is needed.
• For example, air traffic control is a very complex task
needing intense human involvement.
When not to • Also, for very simple tasks which can be
implemented using traditional programming
use ML? paradigms, there is no sense of using machine
learning.
• For example, simple rule-driven or formula-based
applications like price calculator engine, dispute
tracking application, etc. do not need machine
learning techniques.
Application of
ML
Tools for
Machine
Learning
 Department of CE

Thanks
Unit no : 1
Introduction to
Machine Learning
(3170724)

Prof. Hetvy Jadeja