DAYANANDA SAGAR COLLEGE OF ENGINEERING

DEPARTMENT OF MECHANICAL ENGINEERING

(Accredited by NBA Tier-1)
Accredited by National Assessment & Accreditation Council (NAAC) with ’A’ Grade
(AICTE Approved, an Autonomous Institute Affiliated to VTU, Belagavi)
Shavige Malleshwara Hills, Kumaraswamy Layout, Bengaluru-560111

Artificial intelligence and Machine learning

Machine Learning (ML): Machine Learning is a subset of Artificial Intelligence that focuses
on the development of algorithms and statistical models that enable computers to learn from
and make predictions or decisions based on data. In other words, ML allows machines to
improve their performance on a specific task over time without being explicitly programmed.
ML algorithms are designed to identify patterns, relationships, and insights within datasets.
Artificial Intelligence (AI): Artificial Intelligence is a broader field that includes the
development of systems or machines that can perform tasks that typically require human
intelligence. These tasks include reasoning, problem-solving, understanding natural language,
perception, and decision-making. AI can be achieved through various techniques, including
rule-based systems, expert systems, symbolic reasoning, and machine learning. AI aims to
create systems that can simulate human reasoning functions and adapt to different situations.
In summary, machine learning is a subset of artificial intelligence that specifically deals with
developing algorithms to improve a machine's performance on a task through learning from
data, while artificial intelligence is a more comprehensive field that includes various
approaches to create intelligent systems capable of human-like tasks. Machine learning is often
used as a crucial component in many AI applications.
History
First machine learning system was developed in 1950s by Arthur Samuel developed a program
for playing checkers the program was able to observe the position at the game and lern a model
that gives better move for the machine player. The system was played with many games with
the many program and observed that the program was able to play better in the corse of time
with getting more experience of board games. He coined the term ML and defined it as field
of study that gives computers the ability without being explicitly programmed.
Example: For example, in traditional software development, if you wanted a computer to
recognize specific patterns in text, you would write code that explicitly defines the rules and
criteria for identifying those patterns. The computer doesn't learn from data or adapt on its own;
it follows the predetermined set of instructions provided by the programmer.

In contrast, machine learning allows computers to learn and improve their performance on a
task by analyzing data and identifying patterns without being explicitly programmed with all
the rules. The machine learns from examples or data and can make decisions or predictions
based on what it has learned. This is a more data-driven and adaptive approach, where the
machine's behavior is not entirely determined by human programmers but is influenced by the
data it processes.

Page 1|7
 DAYANANDA SAGAR COLLEGE OF ENGINEERING
DEPARTMENT OF MECHANICAL ENGINEERING
(Accredited by NBA Tier-1)
Accredited by National Assessment & Accreditation Council (NAAC) with ’A’ Grade
(AICTE Approved, an Autonomous Institute Affiliated to VTU, Belagavi)
Shavige Malleshwara Hills, Kumaraswamy Layout, Bengaluru-560111

Machine Learning Examples:

Image Recognition: Machine learning models can be trained to recognize objects or patterns
within images. For instance, a machine learning algorithm can be used to identify cats in
photographs.
Recommendation Systems: Websites and applications often use machine learning to
recommend products, movies, or music to users based on their past preferences and behaviors.
Examples include Netflix's movie recommendations and Amazon's product recommendations.
Spam Email Detection: Machine learning algorithms can classify emails as spam or not by
analyzing the content and patterns in emails. This helps in filtering out unwanted emails from
your inbox.
Language Translation: Machine learning is used in language translation services like Google
Translate to understand and translate text from one language to another.
Self-Driving Cars: Autonomous vehicles use machine learning techniques to process data from
sensors, cameras, and radar to make real-time decisions about steering, braking, and
acceleration.
Artificial Intelligence Examples:
Natural Language Processing (NLP): AI systems like chatbots and virtual assistants, such as
Siri and Alexa, use NLP to understand and respond to human language. They can answer
questions, provide information, and perform tasks based on spoken or typed commands.
Game Playing: AI has been used to create systems that can play complex games like chess or
Go at a superhuman level. For example, Deep Blue defeated the world chess champion Garry
Kasparov in 1997.
Medical Diagnosis: AI is employed in medical applications to assist doctors in diagnosing
diseases and conditions. AI systems can analyze medical images (e.g., X-rays, MRIs) or patient
data to provide recommendations for treatment.
Robotics: AI-powered robots are designed to perform tasks in various industries, from
manufacturing to healthcare. For instance, robots in factories can assemble products with high
precision, and surgical robots can assist in complex surgeries.
Autonomous Drones: Drones equipped with AI can navigate autonomously, avoid obstacles,
and perform tasks such as monitoring crops, inspecting infrastructure, or aiding in search and
rescue missions.
Introduction to ML
In general when we have program or algorithm to solve a problem, a computer will solve by
writing a program which takes data as the input and program produces output. On other hand
when we have Machine learning data will be fed to computer as well examples of output which
gives program through which we can solve subsequent problems or decision making.
Page 2|7
 DAYANANDA SAGAR COLLEGE OF ENGINEERING
DEPARTMENT OF MECHANICAL ENGINEERING
(Accredited by NBA Tier-1)
Accredited by National Assessment & Accreditation Council (NAAC) with ’A’ Grade
(AICTE Approved, an Autonomous Institute Affiliated to VTU, Belagavi)
Shavige Malleshwara Hills, Kumaraswamy Layout, Bengaluru-560111

Learning is the ability to improve one’s behaviour with experience. So it is building a

computer system that can automatically improves withs experience
ML explores algorithm that learns from data and builds the model which can be used different
tasks like prediction, decision making, problem solving.
 Mitchell defines ML as computer program is said to learn from experience (E) or data
with respect to some class of tasks (T) and performance measure (P), if a performance
in Tasks (T) as measured by (P) improves with experience (E)
 Here Tasks can be prediction, classification, acting in an environment etc
 Experience is past data used to improve the performance
 Measure of improvement (E) is nothing but improved accuracy in prediction, new skills
for the task which it didn’t had earlier or improve efficiency of problem solving.
Schematic diagram of ML system

Page 3|7
 DAYANANDA SAGAR COLLEGE OF ENGINEERING
DEPARTMENT OF MECHANICAL ENGINEERING
(Accredited by NBA Tier-1)
Accredited by National Assessment & Accreditation Council (NAAC) with ’A’ Grade
(AICTE Approved, an Autonomous Institute Affiliated to VTU, Belagavi)
Shavige Malleshwara Hills, Kumaraswamy Layout, Bengaluru-560111

Application of ML
Medicine:

 Diagnose a disease:
Input: Symptoms, lab measurements, test results, DNA result virus
Output: one of set of possible disease or none of the above.

 Data mine historical medical records to learn which future patient will respond best to
which treatment.
Vision:

 Say What object appear in an image

 Convert hand written digits into characters 0..9
 Detect where object appears in an image
Robot:
Design autonomous mobile robot that learn to navigate from their own experience
NLP (Natural Language Processing):

 Detects what facts are expressed

 Detect a review of product or movie
 Speech recognition
 Machine translation
Financial:

 To predict whether stock rise or fall

 To decide which adds to show
Steps in machine learning

 Choose the training experience or data (Features)

 Choose Target / target function or how to represent a model (To be learned)
 Choose How to represent a target function (Class of function / Hypothesis language)
 Choose learning algorithm to infer target function

What is Machine Learning ?

Arthur Samuel, a pioneer in the field of artificial intelligence and computer gaming, coined
the term “Machine Learning”. He defined machine learning as – a “Field of study that gives
computers the capability to learn without being explicitly programmed”. In a very
layman’s manner, Machine Learning(ML) can be explained as automating and improving the

Page 4|7
 DAYANANDA SAGAR COLLEGE OF ENGINEERING
DEPARTMENT OF MECHANICAL ENGINEERING
(Accredited by NBA Tier-1)
Accredited by National Assessment & Accreditation Council (NAAC) with ’A’ Grade
(AICTE Approved, an Autonomous Institute Affiliated to VTU, Belagavi)
Shavige Malleshwara Hills, Kumaraswamy Layout, Bengaluru-560111

learning process of computers based on their experiences without being actually programmed
i.e. without any human assistance. The process starts with feeding good quality data and then
training our machines(computers) by building machine learning models using the data and
different algorithms. The choice of algorithms depends on what type of data do we have and
what kind of task we are trying to automate. Example: Training of students during exams.
While preparing for the exams students don’t actually cram the subject but try to learn it with
complete understanding. Before the examination, they feed their machine(brain) with a good
amount of high-quality data (questions and answers from different books or teachers’ notes, or
online video lectures). Actually, they are training their brain with input as well as output i.e.
what kind of approach or logic do they have to solve a different kinds of questions. Each time
they solve practice test papers and find the performance (accuracy /score) by comparing
answers with the answer key given, Gradually, the performance keeps on increasing, gaining
more confidence with the adopted approach. That’s how actually models are built, train
machine with data (both inputs and outputs are given to the model), and when the time comes
test on data (with input only) and achieve our model scores by comparing its answer with the
actual output which has not been fed while training. Researchers are working with assiduous
efforts to improve algorithms, and techniques so that these models perform even much better.

Basic Difference in ML and Traditional Programming?

Traditional Programming: We feed in DATA (Input) + PROGRAM (logic), run it on the
machine, and get the output.
Machine Learning: We feed in DATA(Input) + Output, run it on the machine during training
and the machine creates its own program(logic), which can be evaluated while testing.
What does exactly learning mean for a computer? A computer is said to be learning from
Experiences with respect to some class of Tasks if its performance in a given task improves
with the Experience.

Page 5|7
 DAYANANDA SAGAR COLLEGE OF ENGINEERING
DEPARTMENT OF MECHANICAL ENGINEERING
(Accredited by NBA Tier-1)
Accredited by National Assessment & Accreditation Council (NAAC) with ’A’ Grade
(AICTE Approved, an Autonomous Institute Affiliated to VTU, Belagavi)
Shavige Malleshwara Hills, Kumaraswamy Layout, Bengaluru-560111

A computer program is said to learn from experience E with respect to some class of tasks T
and performance measure P, if its performance at tasks in T, as measured by P, improves with
experience E Example: playing checkers. E = the experience of playing many games of
checkers T = the task of playing checkers. P = the probability that the program will win the
next game In general, any machine learning problem can be assigned to one of two broad
classifications: Supervised learning and Unsupervised learning.

How does ML work?

Gathering past data in any form suitable for processing. The better the quality of data, the
more suitable it will be for modelling.
Data Processing – Sometimes, the data collected is in raw form and it needs to be pre-processed.
Example: Some tuples may have missing values for certain attributes, and, in this case, it has
to be filled with suitable values in order to perform machine learning or any form of data
mining. Missing values for numerical attributes such as the price of the house may be replaced
with the mean value of the attribute whereas missing values for categorical attributes may be
replaced with the attribute with the highest mode. This invariably depends on the types of filters
we use. If data is in the form of text or images then converting it to numerical form will be
required, be it a list or array or matrix. Simply, Data is to be made relevant and consistent. It is
to be converted into a format understandable by the machine
 Divide the input data into training, cross-validation, and test sets. The ratio between
the respective sets must be 6:2:2
 Building models with suitable algorithms and techniques on the training set.
 Testing our conceptualized model with data that was not fed to the model at the time
of training and evaluating its performance using metrics such as F1 score,
 precision, and recall.
 Linear Algebra
 Statistics and Probability
 Calculus
 Graph theory
 Programming Skills – Languages such as Python, R, MATLAB, C++, or Octave

Page 6|7
 DAYANANDA SAGAR COLLEGE OF ENGINEERING
DEPARTMENT OF MECHANICAL ENGINEERING
(Accredited by NBA Tier-1)
Accredited by National Assessment & Accreditation Council (NAAC) with ’A’ Grade
(AICTE Approved, an Autonomous Institute Affiliated to VTU, Belagavi)
Shavige Malleshwara Hills, Kumaraswamy Layout, Bengaluru-560111

Machine learning is programming computers to optimize a performance criterion using

example data or past experience . We have a model defined up to some parameters, and learning
is the execution of a computer program to optimize the parameters of the model using the
training data or past experience. The model may be predictive to make predictions in the future,
or descriptive to gain knowledge from data.
The field of study known as machine learning is concerned with the question of how to
construct computer programs that automatically improve with experience.
Definition of learning: A computer program is said to learn from experience E with respect
to some class of tasks T and performance measure P , if its performance at tasks T, as
measured by P , improves with experience E.
Examples
 Handwriting recognition learning problem
Task T : Recognizing and classifying handwritten words within images
Performance P : Percent of words correctly classified
Training experience E : A dataset of handwritten words with given classifications
 A robot driving learning problem
Task T : Driving on highways using vision sensors
Performance P : Average distance travelled before an error
Training experience E : A sequence of images and steering commands recorded while
observing a human driver
Definition: A computer program which learns from experience is called a machine learning
program or simply a learning program.

Page 7|7