AI Project

cycle
Computer Dept
 Lesson
Objectives
Introduction to AI Project
Cycle
Problem Scoping
Data Acquisition
Data Exploration
Modelling
Evaluation
Tuesday, February 2, 20XX Sample Footer Text 2
 Introduction to Project Cycle

• Understanding Project Cycle

• Examples of Project
• Overview of Problems
• Conclusion about Project Cycle

Tuesday, February 2, 20XX Sample Footer Text 3

 In this chapter, we will
Introduction revisit the concept of AI
Project Cycle.

4
1. Introduction

Let us assume that you must make a greeting card for your mother as it is
her birthday. You are very excited about it and have thought of many
ideas to execute the same. Let us look at some of the steps which you
might take to accomplish this task:

1. Look for some cool greeting card ideas from different sources. You
might go online and checkout some videos or you may ask someone
who has knowledge about it.

2. After finalising the design, you would make a list of things that are
required to make this card.

3. You will check if you have the material with you or not. If not, you could
get all the items required, ready for use.

4. Once you have everything with you, you would start making the card.

5. If you make a mistake in the card somewhere which cannot be rectified,

you will discard itSample
Tuesday, February 2, 20XX
and start remaking it.
Footer Text 5
 Are these steps relatable? Noteboo
__________________________________________________________________
k work
______________________________________________________
Do you think your steps might differ? If so, write them down!
__________________________________________________________________
__________________________________________________________________
__________________________________________________________________
__________________________________________________________________
__________________________________________________________________
__________________________________________________________________
__________________________________________________________________
__________________________________________________________________
____________

Tuesday, February 2, 20XX Sample Footer Text 6

These steps show how we plan to execute the tasks around us.
Consciously or Subconsciously our mind makes up plans for every
task which we must accomplish which is why things become
clearer in our mind. Similarly, if we must develop an AI project,
the AI Project Cycle provides us with an appropriate framework
which can lead us towards the goal. The AI Project Cycle mainly
has 5 stages:

PROBLE DATA
M ACQUISITIO DATA MODELLING
EVALUATIO
EXPLORATION N
SCOPING N

Tuesday, February 2, 20XX Sample Footer Text 7

 Stage 1
Problem Scoping:
You set the goal for your AI
project by stating the problem
which you wish to solve with
it. Under problem scoping, we
look at various parameters
which affect the problem we
wish to solve so that the
picture becomes clearer.

Tuesday, February 2, 20XX Sample Footer Text 8

 Problem Scoping
It is a fact that we are
surrounded by problems. They
could be small or big, sometimes
ignored or sometimes even
critical. Many times, we become
so used to a problem that it
becomes a part of our life.
Identifying such a problem and
having a vision to solve it, is
what Problem Scoping is about.

Tuesday, February 2, 20XX Sample Footer Text 9

 Problem
Scoping
We can look at the
Sustainable Development
Goals. 17 goals have been
announced by the United
nations which are termed
as the Sustainable
Development Goals. The
aim is to achieve these
goals by the end of 2030.
A pledge to do so has
been taken by all the
member nations of the
UN

Tuesday, February 2, 20XX Sample Footer Text 10

 Problem Scoping
We use the 4Ws Problem Canvas to help us out. The 4Ws
Problem canvas helps in identifying the key elements related to
the problem. The “Who” block helps in analysing the people
getting affected directly or indirectly due to it.

Tuesday, February 2, 20XX Sample Footer Text 11

Who
Under this, we find out
who the ‘Stakeholders’ to
this problem are and
what we know about
them. Stakeholders are
the people who face this
problem and would be
benefitted with the
solution. Here is the Who
Canvas:
Tuesday, February 2, 20XX Sample Footer Text 12
What?
Under the “What” block, you
need to investigate what you
have on hand. At this stage,
you need to determine the
nature of the problem. What is
the problem and how do you
know that it is a problem?
Under this block, you also
gather evidence to prove that
the problem you have selected
exists. Newspaper articles,
Media, announcements, etc are
some examples. Here is the
What Canvas:
Tuesday, February 2, 20XX Sample Footer Text 13
Where?
Now that you know who is
associated with the problem
and what the problem is;
you need to focus on the
context/situation/location of
the problem. This block will
help you investigate the
situation in which the
problem arises, the context
of it, and the locations
where it is prominent. Here
is the Where Canvas:
Tuesday, February 2, 20XX Sample Footer Text 14
Why?
You have finally listed down all the
major elements that affect the
problem directly. Now it is
convenient to understand who the
people that would be benefitted by
the solution are; what is to be
solved; and where will the solution
be deployed. These three canvases
now become the base of why you
want to solve this problem. Thus,
in the “Why” canvas, think about
the benefits which the
stakeholders would get from the
solution and how it will benefit
them as well as the society.

Tuesday, February 2, 20XX Sample Footer Text 15

 Problem
Statement
Template
After filling the 4Ws
Problem canvas, you now
need to summarize all the
cards into one template.
The Problem Statement
Template helps us to
summarize all the key
points into one single
Template so that in future,
whenever there is need to
look back at the basis of
the problem, we can look at
the Problem Statement
Template and understand
Tuesday, February 2, 20XX Sample Footer Text 16
 Check your Understanding
1. Which of the following is 3. The _____ block helps you in
the first stage of an AI analyzing the stakeholders of
project cycle? the project.
a. What?
a. Data Exploration b. Where?
b. Data Acquisition c. Who?
c. Modelling d. Which?
d. Problem Scoping
4. What do you understand by
2. Which of the following is “Problem Scoping”
not a part of the 4Ws e.
f.
Solution of a problem.
Exploring patterns out of the collected
Problem canvas? g.
data sets.
Developing an algorithm for a problem
a. Who? solution.
b. What? h. Identifying a problem and having the
c. Why?
Tuesday, February 2, 20XX Sample Footer Text vision to solve it. 17
d. Which?
 Solutions
1. Which of the following is 1. The _____ block helps you in
the first stage of an AI analyzing the stakeholders
project cycle? of the project.
a. What?
a. Data Exploration b. Where?
b. Data Acquisition c. Who?
c. Modelling d. Which?
d. Problem Scoping
2. What do you understand by
2. Which of the following is “Problem Scoping”
not a part of the 4Ws a.
b.
Solution of a problem.
Exploring patterns out of the collected
Problem canvas? data sets.
c. Developing an algorithm for a problem
a. Who? solution.
b. What? d. Identifying a problem and having
c. Why?
Tuesday, February 2, 20XX Sample Footer Text the vision to solve it. 18
d. Which?
Stage 2
Data Acquisition:
This stage is about
acquiring data for
the project.

Tuesday, February 2, 20XX Sample Footer Text 19

 What is Data?
Data can be a piece of information or facts and statistics collected for reference or
analysis. Whenever we want an AI project to be able to predict an output, we need to
train it first using data.

For example, If you want to make an Artificially Intelligent system which can predict
the salary of any employee based on his previous salaries, you will feed the data of his
previous salaries into the machine. This is the data with which the machine can be
trained. Now, once it is ready, it will predict his next salary efficiently. The previous
salary data here is known as Training Data while the next salary prediction data set is
known as the Testing Data. For better efficiency of an AI project, the Training data
needs to be relevant and authentic.

In the previous example, if the training data was not of the previous salaries but of his
expenses, the machine would not have predicted his next salary correctly since the
whole training went wrong. Similarly, if the previous salary data was not authentic,
that is, February
Tuesday, it was not correct,
2, 20XX then
Sample too the prediction could have gone wrong. Hence….20For
Footer Text
Data Features
Data features refer to the type of data you want to
collect. In our previous example, data features would
be salary amount, increment percentage, increment
period, bonus, etc.

Tuesday, February 2, 20XX Sample Footer Text 21

Where
can we
get this
data?
There can be
various ways in
which you can
collect data. Some
of them are:

Tuesday, February 2, 20XX Sample Footer Text 22

How to acquire authentic data?
1.Find a reliable source of data from where some authentic
information can be taken.

2.The data which we collect should be open-sourced and not

someone’s property. Extracting private data can be an
offence.

3.One of the most reliable and authentic sources of

information, are the open-sourced websites hosted by the
government.

4.These government portals have general information

collected in suitable format which can be downloaded and
used wisely. Some of the open-sourced Govt. portals are:
Tuesday, February 2, 20XX Sample Footer Text 23
 Check your Understanding
1. Which of the following is not 3. _____ is the one which is
valid for Data Acquisition? used only to assess the
a. Web Scraping performance of a model.
b. Surveys a. Training Data
c. Sensors b. Test data
d. Archives c. Interactive Data
d. Fit Data
2. _____ is the one on which we
4. For the efficient result of
train and fit our model
any AI project, the training
basically to fit the parameters.
1. Training Data data should be relevant to the
e. Problem statement scoped
2. Test Data f. Outsourced
3. Interactive Data g. Free-sourced
4. Fit Data h. Authentic
Tuesday, February 2, 20XX Sample Footer Text 24
 Check your Understanding
1. Which of the following is not 3. _____ is the one which is
valid for Data Acquisition? used only to assess the
a. Web Scraping performance of a model.
b. Surveys a. Training Data
c. Sensors b. Test data
d. Archives c. Interactive Data
2. _____ is the one on which we d. Fit Data
train and fit our model
4. For the efficient result of
basically to fit the parameters.
1. Training Data any AI project, the training
2. Test Data data should be relevant to the
e. Problem statement scoped
3. Interactive Data f. Outsourced
4. Fit Data g. Free-sourced
h. Authentic
Tuesday, February 2, 20XX Sample Footer Text 25
 Stage 3
Data Exploration:
While acquiring data, you must have noticed that the data is a complex
entity – it is full of numbers and if anyone wants to make some sense out
of it, they must work some patterns out of it.
We need to explore and visualize data before jumping into the AI model.
For example, if you go to the library and pick up a random book, you first
try to go through its content quickly by turning pages and by reading the
description before borrowing it for yourself, because it helps you in
understanding if the book is appropriate to your needs and interests or
not.
Similarly, when we get a set of data in our hands, spending time to
explore it will help get a sense of the trend, relationships and patterns
present in the data.
Tuesday, February 2, 20XX Sample Footer Text 26
Why to analyze the data?
To analyse the data, you need to visualise it in some user-
friendly format so that you can:

1.Quickly get a sense of the trends, relationships and patterns

contained within the data.

2.Easily comprehend information.

3.Define strategy for the model to use at a later stage.

4.Communicate the same to others effectively.

To visualise data, we can use various types of visual

Tuesday, February 2, 20XX Sample Footer Text 27
representations.
Are you aware of
visual
representations of
data?

Fill them:

Tuesday, February 2, 20XX Sample Footer Text 28

Tuesday, February 2, 20XX Sample Footer Text 29
Tuesday, February 2, 20XX Sample Footer Text 30
Tuesday, February 2, 20XX Sample Footer Text 31
 Stage 4
Modelling:
When it comes to machines accessing
and analysing data, it needs the data in
the most basic form of numbers (which
is binary – 0s and 1s) and when it comes
to discovering patterns and trends in
data, the machine goes in for
mathematical representations of the
same. The ability to mathematically
describe the relationship between
parameters is the heart of every AI
model. Thus, whenever we talk about
developing
Tuesday, February 2, 20XX
AI models, it is the
Sample Footer Text 32
mathematical approach towards
Classification of AI models

Tuesday, February 2, 20XX Sample Footer Text 33

 Rule Based Approach
The rules are defined by the developer. The machine follows the rules or instructions mentioned by the
developer and performs its task accordingly. For example, we have a dataset which tells us about the
conditions based on which we can decide if an elephant may be spotted or not while on safari. The
parameters are Outlook, Temperature, Humidity and Wind.

Now, let’s take various possibilities of these parameters and see in which case the elephant may be
spotted and in which case it may not. After looking through all the cases, we feed this data into the
machine along with the rules which tell the machine all the possibilities. The machine trains on this
data and now is ready to be tested.
Outlook=Overcas While testing the machine,
Temperature=Normal we tell the machine
Humidity=Nor that
Wind=Weak
t mal

Based on this testing dataset, now the machine will be able to tell if the elephant has been spotted
before or not and will display the prediction to us. This is known as a rule-based approach because we
fed the data along with rules to the machine and the machine after getting trained on them is now able
to predict answers for the same. A drawback/feature for this approach is that the learning is static. The
machine once trained, does not take into consideration any changes made in the original training
dataset. That is, if you try testing the machine on a dataset which is different from the rules and data
you fed it at the training stage, the machine will fail and will not learn from its mistake. Once trained,
the model cannot improvise itself based on feedbacks. Thus, machine learning gets introduced as an
extension to this as in that case, the machine adapts to change in data and rules and follows the
Tuesday, February 2, 20XX Sample Footer Text 34
updated path only, while a rule-based model does what it has been taught once.
 Rule Based Approach
DRAWBACKS:
1.Learning is static:
The machine once trained, does not take into consideration any changes
made in the original training dataset. That is, at the training stage, the
machine will fail and will not learn from its mistake. if you try testing the
machine on a dataset which is different from the rules and data you fed it

2.Cannot improvise itself:

Once trained, the model cannot improvise itself based on feedbacks.

3.Does what it has been taught once

Machine learning gets introduced as an extension to this. The machine adapts
to change in data and rules and follows the updated path only. while a rule-
based model does what it has been taught once.
Tuesday, February 2, 20XX Sample Footer Text 35
 Learning Based Approach
The machine learns by itself.

The AI model gets trained on the data fed to it and then can 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 so that all the exceptions are handled in this case.

For example, suppose you have a dataset comprising of 100 images of apples and
bananas each. These images depict apples and bananas in various shapes and sizes.
These images are then labelled as either apple or banana so that all apple images are
labelled ‘apple’ and all the banana images have ‘banana’ as their label. Now, the AI model
is trained with this dataset and the model is programmed in such a way that it can
distinguish between an apple image and a banana image according to their features and
can predict the label of any image which is fed to it as an apple or a banana. After
training, the machine is now fed with testing data. Now, the testing data might not have
similar images as the ones on which the model has been trained. So, the model adapts to
the features on which it has been trained and accordingly predicts if the image is of an
apple or banana. In this way, the machine learns by itself by adapting to the new data
Tuesday, February 2, 20XX Sample Footer Text 36
which is flowing in. This is the machine learning approach which introduces the
 Learning Based Approach
The learning-based
approach can further be
divided into three parts:
• Supervised Learning
• Unsupervised Learning
• Reinforcement
Learning
Tuesday, February 2, 20XX Sample Footer Text 37
 Supervised Learning
The dataset which is fed to the machine is labelled.

The dataset is known to the person who is training the machine

only then he/she can 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:

Classification: Where the data is classified according to the labels.

For example, in the grading system, students are classified based
on 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.

Regression: Such models work on continuous data. For example, if

Tuesday, February 2, 20XX Sample Footer Text 38
you wish to predict your next salary, then you would put in the
Unsupervised Learning
An unsupervised learning model works on unlabelled dataset.

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
onTuesday,
it. February
After training,
2, 20XX
the machine would produce patterns which it39
Sample Footer Text
Unsupervised learning models can be
further divided into two categories:

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 produce some unique patterns out of it.

Dimensionality Reduction:
We humans can 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
N-Dimensional entities. Which means that we cannot
visualise them as they exist beyond our visualisation
ability. Hence, to make sense out of it, we need to reduce
their dimensions.
Tuesday, February 2, 20XX Here, dimensionality
Sample Footer Text reduction 40
Tuesday, February 2, 20XX Sample Footer Text 41
 Neural Networks
Neural networks are loosely modelled after how
neurons in the human brain behave. It is
essentially a system of organizing machine
learning algorithms to perform certain tasks.
• Advantages:
• They can extract data features automatically
without needing the input of the programmer.

• It is a fast and efficient way to solve problems

for which the dataset is very large, such as in
images.
The larger Neural Networks tend to perform
better with larger amounts of data whereas the
traditional machine learning algorithms stop
improving after a certain saturation point.
Tuesday, February 2, 20XX Sample Footer Text 42
 • A Neural Network is divided into multiple layers and each

How Neural layer is further divided into several blocks called nodes.

• Each node has its own task to accomplish which is then

Networks works? passed to the next layer.

• The first layer of a Neural Network is known as the input

layer. The job of an input layer is to acquire data and feed it
to the Neural Network. No processing occurs at the input
layer.

• Next to it, are the hidden layers. Hidden layers are the
layers in which the whole processing occurs. Their name
essentially means that these layers are hidden and are not
visible to the user.

• Hidden layers has its own machine learning algorithm which

it executes on the data received from the input layer. The
processed output is then fed to the subsequent hidden
layer of the network.

• There can be multiple hidden layers in a neural network

system and their number depends upon the complexity of
the function for which the network has been configured.
Also, the number of nodes in each layer can vary
accordingly.

• The last hidden layer passes the final processed data to the
output layer which then gives it to the user as the final
output.
Tuesday, February 2, 20XX Sample Footer Text 43
 Features of Neural Network

Tuesday, February 2, 20XX Sample Footer Text 44