Artificial Intelligence (AI) :

Artificial Intelligence covers a broad range of domains and

applications and is expected to impact every field in the
future.
Its core idea is building machines & algorithms which are
capable of performing computational tasks that would
otherwise require human like brain functions.

Refers to any technique that enables computers to mimic

human intelligence. It gives the ability to machines to
recognize a human’s face; to move and manipulate objects; to
understand the voice commands by humans, and also do
other tasks.
The AI-enabled machines think algorithmically and execute
what they have been asked for intelligently.
 VENN DIAGRAM

But before this we should know what is to be trained :

AI MODELS :
We have seen various types of graphical representations
which can be used for representing different parameters of
data.
Humans understand graphical representations much better
and can discover trends and patterns from them.
 But when it comes to machines accessing and analyzing
data, it needs the data in the most basic form of numbers
(which is binary – 0s and 1s)
 The ability to mathematically describe the relationship
between parameters is the heart of every AI model.
 Thus, whenever we talk about developing AI models, it is
the mathematical approach towards analyzing data which we
refer to.
Generally, AI models can be classified as follows:
Rule Based Approach
•Refers to the AI modeling where the rules are defined by the
developer.
•The machine follows the rules or instructions mentioned by
the developer and performs its task accordingly.
•That is the algorithm and the data are given by the developer
to give desired outputs.
•They do not have ability to learn by themselves and cannot
improvise according to feedbacks once trained for a dataset.

For Ex : -
- Healthcare Expert Systems (Practo)
-Designing programs for a graph to be plotted.
-Situations using if-then-else conditions and getting the
desired output.
Learning Based Approach :
Refers to the AI modeling where the machine learns by
itself.
Under the Learning Based approach, the AI model gets
trained on the data fed to it and then is able to design a
model which is adaptive to the change in data.
That is, if the model is trained with X type of data and the
machine designs the algorithm around it, the model would
modify itself according to the changes which occur in the data

This approach is of two types:

- Machine Learning
- Deep Learning
Machine Learning (ML)
It is a subset of Artificial Intelligence which 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
Predictions/Decisions. In this the data is given to the model as
labels and its features.
For ex: a picture of dog for features and its label as “DOG”.

Applications of machine learning :

-Email spam filters
- Face recognition and identification (facebook)
- Youtube recommendations
-Shopping sites notifications.
Deep Learning (DL) :
It enables software to train itself to perform tasks with vast
amounts of data without labeling the data.
•In Deep Learning, the machine is trained with huge amounts
of data which helps it in training itself around the data.
•Such machines are intelligent enough to develop algorithms
for themselves using artificial neural networks.

Example :
Sophia humanoid

https://www.youtube.com/watch?v=ukzFI9rgwfU machine learning

https://youtu.be/2ePf9rue1Ao AI in 5 mins
Just look at the picture and try to analyze the process

Discussed ??
Now we will see how are they categorized….
The learning-based approach can further be divided into
three parts:
 Supervised Learning
 In a supervised learning model, the dataset which
is fed to the machine is labelled.
 In other words, we can say that the dataset is
known to the person who is training the machine
only then he/she is able to label the data.
 A label is some information which can be used as a
tag for data.
For example, students get grades according to the
marks they secure in examinations. These grades are
labels which categorise the students according to
their marks.
There are two types of Supervised Learning models
1. Classification:
Where the data is classified
according to the labels.

For example, in the grading

system, students are classified
on the basis of the grades they
obtain with respect to their
marks in the examination. This
model works on discrete dataset
which means the data need not
be continuous.
2. Regression:
Such models work on
continuous data.

For example, if you wish to

predict your next salary, then
you would put in the data of
your previous salary, any
increments, etc., and would
train the model. Here, the data
which has been fed to the
machine is continuous.
 Unsupervised Learning
 An unsupervised learning model works on un-
labelled dataset.
 This means that the data which is fed to the
machine is random and there is a possibility that
the person who is training the model does not have
any information regarding it.
 The unsupervised learning models are used to
identify relationships, patterns and trends out of
the data which is fed into it.
 It helps the user in understanding what the data is
about and what are the major features identified
by the machine in it.
For example,
you have a random data of 1000 dog images and you wish to
understand some pattern out of it, you would feed this data
into the unsupervised learning model and would train the
machine on it.
After training, the machine would come up with patterns
which it was able to identify out of it. The Machine might
come up with patterns which are already known to the user
like color or it might even come up with something very
unusual like the size of the dogs.

Image
 Unsupervised learning models can be divided into two
categories
1.Clustering:
Refers to the unsupervised
learning algorithm which
can cluster the unknown
data according to the
patterns or trends identified
out of it. The patterns
observed might be the ones
which are known to the
developer or it might even
come up with some unique
patterns out of it.
2. Dimensionality Reduction:
We humans are able to visualise up to 3-Dimensions only but
according to a lot of theories and algorithms, there are
various entities which exist beyond 3-Dimensions.
• For example, in Natural language Processing, the words
are considered to be N-Dimensional entities. Which means
that we cannot visualise them as they exist beyond our
visualisation ability.(i.e. we have been taught these
symbols for speaking and identifying alphabets and word
other wise it is phonetics)
Hence, to make sense out of it, we need to reduce their
dimensions. Here, dimensionality reduction algorithm is used.
As we reduce the dimension of an entity, the information
which it contains starts getting distorted.
One More Example can be like ,
If we have a ball in our hand, it is 3-Dimensions right now.
But if we click its picture, the data transforms to 2-D as an
image which is a 2-Dimensional entity.

Now, as soon as we reduce one dimension, at least 50% of the

information is lost as now we will not know about the back of
the ball. Whether the ball was of same colour at the back or
not? Or was it just a hemisphere? If we reduce the
dimensions further, more and more information will get lost.

Hence, to reduce the dimensions and still be able to make

sense out of the data, we use Dimensionality Reduction.
 Reinforcement Learning
 Reinforcement learning, in the context of artificial intelligence, is
a type of dynamic programming that trains algorithms a system
of reward and punishment.

 A reinforcement learning algorithm learns by interacting with its

environment.

 The model receives rewards by performing correctly and

penalties for performing incorrectly.

 The model learns without intervention from a human by

maximizing its reward and minimizing its penalty.

 The model learns from the feedback that it receives from the
environment edits data it has or adds new data for further
rewards.
 For Example :
 From the previous example of dogs in
unsupervised learning the features were identified.

 But now in a new situation a new type of dog with

varied features is shown to the model for
identification, it will try to match patterns and
reply but if it gets a negative feedback the model
will capture the new features and record them for
further correct identification in next turn.

 And will get rewards in the next identification.

This is called Reinforcement learning.