Scribd
Upload
46 views27 pages

Understanding AI Project Life Cycle

Uploaded by

arjunmanojnair2010
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
46 views27 pages

Understanding AI Project Life Cycle

Uploaded by

arjunmanojnair2010
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 27

Chapter 2

Understanding AI
Project Life Cycle
AI and Sustainable Development
Goals
AI Project Cycle
Problem Scoping
Problem Scoping
This is the initial stage where you define the problem you want to
solve. It involves understanding the problem in depth and
identifying the key factors that affect it.
The 4Ws framework is often used here:
•Who: Identifies the stakeholders affected by the problem.

•What: Defines the nature of the problem and gathers evidence


to prove its existence.

•Where: Specifies the location or context where the problem


arises.

•Why: Explains why the problem is worth solving.


Data Acquisition
Data Acquisition

In this stage, you collect accurate and reliable data that will be
used to address the problem.

This data can come from various sources such as surveys,


experiments, or online databases.

The goal is to gather enough relevant data to work with.


Data Exploration
Data Exploration

Once the data is collected, it needs to be organized and analyzed. This


stage involves cleaning the data, handling missing values, and identifying
patterns or trends. Visualization tools can be helpful here to make sense of
the data.
Modelling
Modeling

Modeling involves creating algorithms or models that can learn from the
data and make predictions or decisions. This stage includes selecting the
right type of model, training it with the data, and fine-tuning it to improve
its performance.
Evaluation
Evaluation

The final stage is to evaluate the model’s


performance. This involves testing the model with new
data to see how well it performs and making any
necessary adjustments. Evaluation helps ensure that
the model is accurate and reliable.
4Ws Problem Canvas
Who?
 The “Who” block helps in analysing the people getting
affected directly or indirectly due to it.
 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.
What?
 Under the “What” block, you need to look into what you
have on hand.
 need to determine the nature of the problem.
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 look into the situation in which the
problem arises, the context of it, and the locations where it
is prominent.
Why?
 These three canvases now become the base of why you
want to solve this problem.
 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.
 After filling the 4Ws Problem canvas, you
now need to summarise all the cards into
one template.
System Maps
 System maps helps us to find the
relationships between different elements of
the problems which we have scoped.
 System: An interconnected set of elements

that is organized in a way that achieves


something.
 The main use of system map is to structure

a system and communicate the result to


others.
 Allows to clarify thoughts at an early stage.
A system map comprises :
◦ Elements:
Different ,discrete elements in a system( Eg: organs in
a human body)
◦ Interconnections : These are the relationship
between the elements.(predator –pray
relationship)
Link to make System maps online: https://ncase.me/loopy/
Create a 4W Project Canvas for the
following: As more and more new
technologies get into play, risks will get
more concentrated into a common
network. Cybersecurity becomes extremely
complicated in such scenarios and goes
beyond the control of firewalls. It will not
be able to detect unusual activity and
patterns including the movement of data.
Think how AI algorithms can scrape
through vast amounts of logs to identify
susceptible user behaviour. Use an AI
project cycle to clearly identify the scope,
how you will collect data, model and
evaluation parameters.
Data Acquisition
 this stage is about acquiring data for the
project.
 Data can be a piece of facts and statistics
collected together 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 better efficiency of an AI project, the
Training data needs to be relevant and
authentic.
Data Features
 Data features refer to the type of data you
want to collect.
 Eg: data features would be salary amount,

increment percentage, increment period,


bonus, etc.
 Data collected should be authentic , reliable

, accurate and open sourced.


 Extracting private data can be an offence.
Sources of Data collection
Types of Data
 For data science the data is collected in the
forms of tables.
 The tabular data sets can be stored in

different formats:
◦ CSV: Comma Separated Values
◦ Spreadsheets: A piece of programs or a computer
program which is used to record data in the form
of rows and columns.
◦ SQL: Structured Query Language , It is a
programming language designed do for managing
data held in different kind of DBMS
Data Exploration
 to analyse the data, you need to visualise it
in some user-friendly format so that you
can:

◦ Quickly get a sense of the trends, relationships and


patterns contained within the data.
◦ Define strategy for which model to use at a later stage.
◦ Communicate the same to others effectively.
◦ To visualise data, we can use various types of visual
representations.
Types of Visual
Representations
https://datavizcatalogue.com/
Visit the site and write note
Data Visualization Technique1:
Name:
Description in one-line:
Suitable for which data type:
How to draw it:
Data Visualization Technique2:
Name:
Description in one-line:
Suitable for which data type:
How to draw it:
MODELLING
 When machines accessing data and analysing data, it
needs the data in the very basic form-(binary).

 The ability to mathematically describe the relationship


between parameters is the heart of AI model.

 Modelling is the mathematical approach towards


analysing data.

 there are two approaches:


◦ Rule based
◦ Learning based
 Machine learning
 Deep Learning
Rule Based Approaches
 A rule-based system uses rules as the
knowledge representation .
 The rules are coded into the system in the

form of a series of if-then-else statement


that guides a computer to reach a
conclusion or recommendation.

You might also like