How does ML Machine Learning

What is Machine Learning?

Works? Process

Artificial Intelligence vs What is Deep Machine Learning vs

Machine learning Learning? Deep Learning

As you have been progressing towards building AI readiness, you must have come across a very
common dilemma between Artificial Intelligence (AI) and Machine Learning (ML).

Many times, these terms are used interchangeably but are they the same? Is there no difference
between Machine Learning and Artificial Intelligence? Is Deep Learning (DL) Also Artificial
Intelligence? What exactly is Deep Learning? Let us see

This Flow chart will help us get an overview of Artificial Intelligence

To read about Artificial Intelligence Go to What is AI & What Not ? and Human
vs Artificial Intelligence

Now you should be sure about what AI is, So we can jump to what is Machine learning below.

What is Machine Learning (ML)? 

It is a subset of Artificial Intelligence that enables machines to improve at tasks
with experience (data).

The intention of Machine Learning is to enable machines to learn by themselves

using the provided data and make accurate algorithms for Predictions/ Decisions.

Now let’s understand Machine Learning in a simple way. In literal Machine Learning is “Machine”
+ “Learning”.

It means that Associating Machines with Learning. Let’s go dig it out

How Machine Learning works ?

Machines Learn in a similar manner in which humans learn. Well, let’s quickly see How Humans
Learn?

How Humans Learn ?

To understand the human learning process, let us illustrate it through a simple sequence of
activities involved.

Machine Learning Process (ML) 

A computer learns in a similar way. However, it needs a lot of information, to
ensure that it recognizes things accurately. Machines need to be trained to make
decisions and to act based on goals

How to Train Machines? Computers need a lot of information to ensure accurate

recognition of things

Let’s take an example, now think, how can a computer recognize a flame?

This could be using color, size, shape, origin, temperature,

etc. Once it recognizes the flame, it needs to be trained to
make the decision to act, as in this case, whether it should
touch the flame or not?
This is based on the goals set for the computer.

For example, a computer sets the goal to extinguish the

flame by touching or stamping. So, it will see a flame and
act to touch it and extinguish it, whereas another way to
avoid burning and damage is to see a flame as a danger
and not to touch it.

Now think, how will a computer differentiate between an actual flame and a photo of the flame?

Actual Flame
Photo

A wrongly trained computer may try and extinguish the flame in the painting or touch a live flame
again to get damaged. So, is it possible that they can discern based on temperature, movement,
etc?

Capability of Machines
To make the machine learn, first we need to see the capability of the machine.

Capabilities of a Machine:- [hide]

1 Cameras for capturing images.

2 Receivers for capturing sound.

3 Convertors and Speakers to produce sound.

4 We Can provide them with sensing devices that can act like skin, eyes, ears, mouth,
and noses . Some of these are called sensors.
5 Sensors are man-made (artificial) devices, usually made of specific materials and
connected using electronic signals. They sense chemicals, waves, light, and other things
and interpret them

Artificial Intelligence vs Machine learning 

But even though both AI and ML are based on statistics and mathematics, they are not the same
thing.

Artificial Intelligence Machine learning

It is the study of how to train computers so Machine Learning is the learning in which a
that computers can do things which at machine can learn on its own without being
present humans can do better. explicitly programmed.

Perform tasks that require human Helps machines to learn certain things on
intelligence. their own.

The aim is to increase the chance of success The aim is to increase accuracy, but it does
and not accuracy. not care about success.

It works as a computer program that does it is a simple concept machine that takes
smart work. data and learns from data.

ML allows systems to learn new things from

AI is decision making
data.

AI leads to intelligence or wisdom. ML leads to knowledge.

AI try to make machines intelligent that can take accurate decisions, whereas ML
try to train machines to do certain tasks

What is Deep Learning? 

Deep learning is a type of machine learning and artificial intelligence (AI) that imitates the way
humans gain certain types of knowledge.
Deep learning is an important element of data science, which includes statistics and predictive
modeling.

Deep Learning have very complex algorithms and require very large amount of
dataset.

Deep learning utilizes both structured and unstructured data for training.
Practical examples of deep learning are Virtual assistants, vision for driverless cars, money
laundering, face recognition and many more.

Deep learning is an AI function that mimics the workings of the human brain in processing data for
use in detecting objects, recognizing speech, translating languages, and making decisions.

How Deep Learning works :

Deep learning is based on ML but it can work with unstructured data and learns on its own
through reading the data, so it requires large amount of datasets called Big Data which is drawn
from sources like social media, internet search engines, e-commerce platforms,etc.

These datasets are then processed through complex ML algorithms.

Machine Learning vs Deep Learning 

Machine Learning Deep Learning

Machine Learning is a superset of Deep Deep Learning is a subset of Machine

Learning Learning

The data represented in Machine Learning is The data representation is used in Deep
quite different as compared to Deep Learning as Learning is quite different as it uses
it uses structured data. neural networks(ANN).

Machine learning consists of thousands of data

Big Data: Millions of data points.
points.

Machine Learning is highly used to stay in the Deep Learning solves complex machine
competition and learn new things. learning issues.

Your data is used by companies to do deep learning and make products on

current trend in mentality and what people likes.