SKD Academy (CBSE)

Session -2025-2026
Class – X
Subject – Artificial Intelligence (417)
Unit 2 – Advance Concepts of Modelling in AI
AI, ML, DL
Feature Artificial Machine Learning Deep Learning
Intelligence (AI) (ML) (DL)
AI is the science of ML is a subset of AI DL is a subset of ML
making machines that enables machines that uses neural
Definition
imitate human to learn from data. networks to simulate
behavior. human brain.
To create smart To enable systems to To mimic human
Goal systems. learn and improve from brain to process
data. data.
Siri, Self-driving car Email spam filter, Face recognition,
Example
movie recommendation language translation
Data Can work with small Needs structured data Requires large
Requirement data datasets
Rule-based, search, Decision Tree, CNN(Convolutional
logic, ML-based SVM(Support Vector neural network),
Machine ), KNN (K- RNN(Recurrent
Algorithms nearest neighbor Neural Network),
algorithm) ANN(Advanced
Network
Management.)

Common Terminologies Used with Data

Term Definition Example
A collection of data used for analysis or CSV file containing
Dataset
model training. housing prices.
Input variables used for predictions. In house price
Features
prediction: size,
(Variables)
location, bedrooms.
Labels The output variable to be predicted. Actual house price in a
(Target) dataset.
Data used to train the model. 70% of a dataset used
Training Data
for learning patterns.
Data used to evaluate model performance. Remaining 30% of the
Testing Data
dataset.
Model performs well on training data but A complex model
poorly on new data. memorizes training
Overfitting
data instead of
generalizing.
 Model fails to capture underlying patterns A too-simple model
in data. performs poorly on
Underfitting
both training and test
data.
Bias: Error due to High bias:
Bias &
oversimplification. Variance: Error due to Underfitting. High
Variance
overcomplexity. variance: Overfitting.

Types of AI Models
Type Definition Example
Rule-Based AI Follows predefined logical Basic chatbots with if-else
rules. conditions.
Machine Learning Learns patterns from data. Decision trees, neural
Models networks.
Deep Learning Uses multi-layered neural CNNs for image recognition,
Models networks. RNNs for text.
Generative AI Creates new data similar to ChatGPT, DALL·E (image
input data. generation).

Rule-Based vs. Learning-Based Approach

Aspect Rule-Based Approach Learning-Based Approach
Definition Uses predefined rules and logic. Learns patterns from data.
Flexibility Rigid, hard to modify. Adaptable, improves with more data.
Example Basic automated customer Spam detection using ML.
support.
Pros Transparent, easy to debug. Handles complex, unstructured data.
Cons Fails with new scenarios. Requires large datasets, black-box
nature.

Machine Learning (ML)

The machine learns from its mistakes and takes them into consideration in the next
execution. It improvises itself using its own experiences.

Examples of Machine Learning (ML)

 a) Object Classification – Object classification refers to the process of identifying
and categorizing specific objects within an image or video. For example, there
is an image with multiple animals; if you want to categorize or identify a specific
animal, then it is only possible with machine learning.
b) Anomaly Detection – Anomaly detection helps us find the unexpected things
hiding in our data. For example, tracking your heart rate, and finding a sudden
spike could be an anomaly, flagging a potential issue.
Deep Learning (DL)
Deep learning analyzes the data, learns the data and solves the problem the same as a
human. Deep learning requires the machine to be educated with a large quantity of
data in order to train itself.

Examples of Deep Learning (DL)

a) Object Identification – Object classification in deep learning tackles the task
of identifying and labeling objects within an image. It essentially uses powerful
algorithms to figure out what’s in a picture and categorize those things.
b) Digit Recognition – Digit recognition in deep learning tackles the challenge of
training computers to identify handwritten digits (0-9) within images.
Common terminologies used with data
What is Data?
Data is information in any form For e.g. A table with information about fruits is data,
Each row will contain information about different fruits. Each fruit is described by
certain features.

What do you mean by Features?

Columns of the tables are called features, In the fruit dataset example, features may be
name, color, size, etc., Some features are special, they are called labels
What are Labels?
Data Labeling is the process of attaching meaning to data. For e.g. if we are trying to
predict what fruit it is
based on the color of the fruit, then color is the feature, and fruit name is the label.
Data can be of two types – Labeled and Unlabeled

What are Labeled Data?

Data to which some tag/label is attached is known as labeled data. For example, name,
type, number, etc. Unlabeled data is a raw form of data that has no tag attached.
What do you mean by a training data set?
The training data set is a collection of examples given to the model to analyze and
learn. Just like Veer Sir teaches a topic to the class through a lot of examples and
illustrations. Similarly, a set of labeled data is used to train the AI model.
What do you mean by a testing data set?
The testing data set is used to test the accuracy of the model. Just Veer Sir takes a
class test related to a topic to evaluate the understanding level of students. Test is
performed without labeled data and then verify results with labels.
Modelling
An AI model is a program that uses algorithms to analyze data and make decisions
without human intervention. AI models are trained on data sets to recognize patterns
and perform tasks.
There are two different approaches in AI models

a) Rule Based Approach

b) Learning Based Approach
Rule Based – Rule Based AI modelling where 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, Rule-based Chatbots are commonly used on
websites to answer frequently asked questions (FAQs) or provide basic customer
support.

A drawback of the rule-based approach

a) In a rule-based approach, the learning is static.
b) Once trained, the machine will not make any changes in the training dataset.
Learning Based – Refers to the AI modelling 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.

The learning-based approach can further be divided into three parts:

1. Supervised Learning
2. Unsupervised Learning
3. Reinforcement Learning
1. Supervised Learning
Supervised learning is a machine learning technique that uses labeled data to train
algorithms to predict outcomes. In a supervised learning model, the dataset which is
fed to the machine is labelled.
There are two types of Supervised Learning models:
a. 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.

Examples of the Classification Model

Classifying emails as spam or not: The model is shown tons of emails, both real
ones (like from friends or colleagues) and spam. The model learns what makes an email
look like spam. Once trained, the model sees a new email. It analyzes the clues in the
email and decides: is this spam or not? It assigns a category – “spam” or “not spam” –
just like sorting your mail.
b. 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.
2. Unsupervised Learning
An unsupervised learning model works on unlabeled 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.

Unsupervised learning models can be further divided into two categories:

a. 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.

What is the difference between Clustering and Classification?

❖ Classification uses predefined classes in which objects are assigned.
 ❖ Clustering finds similarities between objects and places them in the same
cluster and it differentiates them from objects in other clusters.

b. Association- Uses different rules to find relationships between variables in a given

data set. This is a data mining technique used for better understanding of customer
purchasing patterns based on relationships between various products.

Based on the purchase pattern of customers A and B, can you predict any Customer X
who buys bread will most probably buy?

3. Reinforcement Learning
This learning approach enables the computer to make a series of decisions that
maximize a reward metric for the task without human intervention and without being
explicitly programmed to achieve the task. It’s based on a trial-and-error learning
process to achieve the goals.
Examples of reinforcement learning are question and answering, machine
translation, and text summarization.
Difference between supervised and unsupervised Learning?
Supervised Learning Unsupervised Learning

Deals with labelled data Deals with unlabeled data

Useful in real-world problems like Useful in finding unknown patterns within data
predicting the prices of an item like making sence of a large number of
something based on past trends. observations from an experimental device.

Computing power required is The computing power required is more

simpler as clean labelled data is complex as unsorted and messy data is used
used as input. as input

Sub-Categories of Deep Learning

Deep learning is the most advanced form of artificial intelligence.
Subcategories of Deep Learning:
1. Artificial Neural networks (ANN)
2. Convolutional Neural Network (CNN)

1. Artificial Neural networks (ANN)- Neural networks are modelled on the human
brain and nervous system. They are able to automatically extract features without input
from the programmer. Every neural network node is essentially a machine learning
algorithm. It is useful when solving problems for which the data set is very large.

How neural networks work:

Neurons are known as nodes. An artificial neural network has an input layer, an output
layer, and hidden layers. The input layer is responsible for receiving the data from
the real world, and all the input data passes through one or multiple hidden layers and
transforms the result using the output layer.
The structure of an entire artificial neural network consists of
a) Input layer – takes input data and transfers it to the hidden layer of neurons
using synapses.
b) Hidden layer – takes data from the input layer to categorize the data and send
it to more hidden layers and finally send it to the output layer.
c) Output layer – takes the data from the hidden layer and generates the result.

2. Convolutional Neural Network (CNN)

A convolutional neural network (CNN) is a category of machine learning model.
Specifically, it is a type of deep learning algorithm that is well suited to analyzing visual
data. CNNs are commonly used to process image and video tasks. And, because
CNNs are so effective at identifying objects, they are frequently used for computer
vision tasks, such as image recognition and object recognition, with common use cases
including self-driving cars, facial recognition and medical image analysis.

Q- Convert the following scenarios to perceptron-

1) Context: A manager is deciding whether to approve a work-from-home request
from an employee.
Factors: –
a) Does the employee perform well when working remotely? –
b) Are there any upcoming team meetings or collaborative projects? –
c) Does the company’s policy support remote work? –
d) Is it beneficial for both the employee and the company?
Answer -

a) Inputs Factors: Employee remote performance, upcoming team

meetings/projects, company policy on remote work, benefits for employee and
company.
 b) Weights: Importance of each factor.

c) Threshold: Decision boundary for approval.

d) Output: Approve (1) or Deny (0).

2) Context: A homeowner is deciding whether to invest in solar panels for their house.
Factors: –
a) Do I have a sufficient average amount of sunlight in my area?
b) Are there any available incentives or rebates for installing solar panels?
c) Does installing solar panels impact the value of my home?
d) Does solar energy lead to environmental benefits?

Answer

a) Inputs (Factors): Average sunlight, available incentives/rebates, impact on

home value, environmental benefits.

b) Weights: Importance of each factor.

c) Threshold: Decision boundary for investment.

d) Output: Invest (1) or Not Invest (0).