AI PROJECT
CYCLE
- HARSHIT X A R.NO-13
LEARNING
OUTCOMES
• Introducing AI Project
Cycle
• Stages of AI Project Cycle
• Neural Networks
• Project cycle is the steps taken to
complete a task from the beginning to
its end. AI project cycle provides us
with a framework of planning,
INTRODUCING organising, executing and
AI PROJECT implementing an AI project to achieve
a target.
CYCLE
• Understanding the different stages
of AI project cycle will help you learn
the importance of each and
every steps in designing an AI Project.
S TA G E S O F A I
PROJECT CYCLE
There are mainly five stages of
developing an AI Project:
1. Problem Scoping
2. Data Acquisition
3. Data Exploration
4. Modelling
5. Evaluation
S TA G E 1 : P R O B L E M S C O P I N G
This is the first and the crucial stage of AI Project development which focuses on
identifying and understanding problems using 4Ws- Who, What , Where & Why.
WHO? WHAT? WHERE? WHY?
Who are the Determine the nature Focus on the Think about the benefits
of the problem. context/situation/locat which the stakeholders
'STAKEHOLDER would get from the
ion of the problem.
S'. solution.
S TA G E 2 : D ATA A C Q U I S I T I O N
• This is the second stage of the AI project cycle. It is the process of collecting data
required for training the AI project. Data is raw information that is used to generate
meaningful outcomes.
DATA FEATURES-
Data features refers to the type of data to be collected.
The data can be collected through:
SURVEYS, WEB SCRAPING , SENSORS, CAMERAS , OBSERVATIONS , APPLICATION
PROGRAMME INTERFACE (API)
S TA G E 3 : D ATA E X P L O R AT I O N
• This is the third stage in the AI project cycle. It refers to exploring the large
data to uncover the patterns or trends needed for the AI project.
Tools for Data Exploration
Google Charts Tableau Fusion Charts High Charts
S TA G E 4 : D ATA M O D E L L I N G
• An important stage in the process of AI project cycle where we decide on the technique to
be followed for building a model from the prepared data.
RULE BASED APPROACH
• This approach is based on a set of rules and facts defined by the developer and fed to the
machine to perform its task accordingly to generate the desired output. These models
can operate with simple basic information and data.
LEARNING BASED APPROACH
• This approach refers to the mode where the relationship or patterns in the data are not
defined by the developer. Random data is fed into the machine and machine develops its
own pattern or trends based on data outputs
SUPERVISED UNSUPERVISED
LEARNING LEARNING
In a supervised learning An unsupervised
model is given to the learning approach
machine. works on an unlabelled
dataset. This means the
It's further categorised data which is fed to
SUPERVISED into:- the machine is random
and there is no knowhow
VS REGRESSION available about it to the
CLASSIFICATION trainer.
UNSUPERVISE
It's further divided into:-
D LEARNING CLUSTERING
DIMENSIONALITY
REDUCTION
S TA G E 5 : E VA L U AT I O N
• This is a very important stage of AI Project designing and training where we actually test
the system to find out the efficiency and performance of the model.
NEURAL
NETWORKS
• Neural Networks form a base of
Deep learning, a subfield of Machine
learning where algorithms
are inspired by the structure of human
brain. Neural networks take in data , train
themselves to recognise the patterns in
this data and then predict the outputs for a
new similar data. The most
impressive aspect of neural networks is that
once trained, they learn on their own just
like human brains.
I M P O RTA N T
F E TA U R E S O F
NEURAL
NETWORKS
• The model of the AI Neural network is
based on the human neural network
i.e. , brain and Nervous system.
• They are designed in such a way that
the information can be
automatically extracted without the
interaction of the programmer.
• Every node of a neural
network system is a
machine learning alorithm.
• It is best suited for AI
models dealing with large data.
