CLASS X

SESSION 2024-25
AI PROJECT CYCLE-HANDOUTS

The AI Project Cycle is a systematic framework consisting of five stages: Problem Scoping, Data
Acquisition, Data Exploration, Modelling, and Evaluation. This cycle guides the development of AI
projects, ensuring a structured approach to identifying problems, gathering and analyzing data.

Need to develop AI project cycle

The AI Project Cycle ensures a systematic, structured approach to developing AI projects, enhancing
clarity, efficiency, and accuracy from problem definition to solution evaluation

Introduction to AI Project Cycle

The AI Project Cycle consists of several key stages that guide the development of an AI
project from conception to completion. These stages are:

1. Problem Scoping
2. Data Acquisition
3. Data Exploration
4. Modeling
5. Evaluation

Problem Scoping

Objective: Identify and define the problem that needs to be solved.

Key Steps:

 Understand the Problem: Discuss with stakeholders to understand the issue.

 Define the Problem Statement: Write a clear and concise problem statement.
 Identify Goals: Determine what you aim to achieve with the AI solution.
 Specify Constraints: Identify any limitations such as time, budget, or data
availability.

Example: If you want to predict student grades, the problem statement might be: "Predict the
final grades of students based on their performance in assignments, attendance, and test
scores."

To demonstrate how the 4W Canvas is utilized to understand and address the problem of
improving student performance through an AI project cycle.

Applying the 4W Canvas

Using the 4W Canvas, the problem is scoped as follows:

Who: Students, teachers, parents, and school administrators.

What: Students are unable to improve their final grades despite regular effort and
participation.

Where: Schools, particularly in classrooms and during assessment periods.

Why: Improving grades enhances academic opportunities, personal development, and

educational equity.

Solution of this problem is to Integrate the AI model into the school's existing systems to
regularly monitor the system's performance and update the model with new data.

Data Acquisition

Objective: Gather the data required to solve the problem.

Key Steps:

 Identify Data Sources: Determine where to get the data (e.g., databases, online
repositories).
 Collect Data: Gather data from identified sources.
 Ensure Data Quality: Check for and address any issues such as missing or
inconsistent data.

Example: For predicting student grades, data could include students' assignment scores,
attendance records, and test scores.

4. Data Exploration

Objective: Understand the data and its characteristics.

Key Steps:

 Data Cleaning: Remove or correct any errors in the data.

 Data Visualization: Use charts and graphs to visualize data distributions and
relationships.
 Statistical Analysis: Perform basic statistical analyses to understand data trends and
patterns.

Example: Visualize the distribution of test scores and find correlations between attendance
and grades.

5. Modeling

Objective: Develop a model to solve the problem.

Key Steps:

 Select Algorithms: Choose appropriate machine learning algorithms based on the

problem.
 Train the Model: Use training data to teach the model to make predictions.
 Validate the Model: Use validation data to check the model's performance and adjust
as necessary.

Machine learning is a subset of artificial intelligence where systems learn from data to make
predictions or decisions. The main types of machine learning are supervised learning,
unsupervised learning, and reinforcement learning.

1. Supervised Learning

Definition: Supervised learning involves training a model on a labeled dataset, meaning that
each training example is paired with an output label. The goal is to learn a mapping from
inputs to outputs.

Types:

 Classification: Predicts categorical labels.

o Example: Email spam detection where emails are classified as "spam" or "not
spam."
 Regression: Predicts continuous values.
o Example: House price prediction based on features like size, location, and
number of bedrooms.

Example Scenario: Predicting student grades based on historical data. The model is trained
with past student records (inputs) and their corresponding final grades (outputs).

2. Unsupervised Learning

Definition: Unsupervised learning involves training a model on data that does not have
labeled responses. The goal is to infer the natural structure present within a set of data points.

Types:

 Clustering: Groups data points into clusters based on their similarity.

o Example: Customer segmentation in marketing, where customers are grouped
based on purchasing behavior.
 Dimensionality Reduction: Reduces the number of random variables under
consideration.
o Example: Principal Component Analysis (PCA) used to simplify data
visualization and reduce noise.

Example Scenario: Grouping students based on their learning styles and performance
patterns. The model identifies clusters of students who exhibit similar behaviors and learning
outcomes without predefined labels.
3. Reinforcement Learning

Definition: Reinforcement learning is a type of learning where an agent learns to make

decisions by taking actions in an environment to maximize cumulative rewards. The agent
receives feedback in the form of rewards or penalties.

Example Scenario: Training a virtual tutor to provide personalized teaching strategies. The
tutor learns the most effective methods for different types of students by receiving feedback
on student progress and adapting its strategies to maximize learning outcomes.

6. Evaluation

Objective: Assess the performance of the model.

Key Steps:

 Performance Metrics: Determine which metrics to use (e.g., accuracy, precision,

recall).
 Test the Model: Use test data to evaluate how well the model performs.
 Compare Results: Compare the model's predictions with actual outcomes to assess
accuracy.

Example: Evaluate the prediction model by comparing the predicted grades with actual
grades and calculating the accuracy.

Neural Networks

Neural networks are loosely modelled after how neurons in the human brain behave. The key
advantage of neural networks are that they are able to extract data features automatically without
needing the input of the programmer. A neural network is essentially a system of organizing
machine learning algorithms to perform certain tasks. It is a fast and efficient way to solve problems
for which the dataset is very large, such as in images.

A Neural Network is divided into multiple layers and each layer is further divided into several blocks
called nodes. Each node has its own task to accomplish which is then 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.

Each node of these 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. Similar to the input layer,
output layer too does not process the data which it acquires. It is meant for user-interface.