ARTIFICIAL

INTELEGENCE

Class 10
E
Strictly based on CBS

Sample Paper
Question Bank

Chapter Wise
Simplified Notes

Topic Wise
Important Questions

www.SinghClasses.in As per the latest Board Syllabus issued by CBSE 2024

ROHIT SINGH
 INTRODUCTION TO ARTIFICIAL INTELLIGENCE (11 MARKS)
AI refers to the simulation of human intelligence to machines that can mimic human traits to perform cognitive tasks like thinking,
learning, and decision-making. Applications of Artificial Intelligence: Voice Assistant, Chat Bot and recommendation system etc.

DOMAIN OF ARTIFICIAL INTELEGENCE SUBSET OF ARTIFICIAL INTELEGENCE

Computer Vision is the ability of computers to understand Artificial Intelligence is a branch of computer science refers
and interpret visual information. Examples include self- to any technique that enables machine to mimic human
QCOMPUTER VISION: THE ABILITY QCOMPUTER
intelligence.
VISION: THE ABILITY
driving cars and facial recognition systems.
OF COMPUTERS TO UNDERSTAND OF COMPUTERS TO UNDERSTAND
Natural Language Processing provide the interaction Machine Learning is a subset of AI that allows machines to
AND INTERPRET VISUAL
between computers and humans using natural language.
AND INTERPRET VISUAL
learn from data and improve their performance over time
INFORMATION.
Examples include email EXAMPLES
filters, autocorrectINCLUDE
features, and INFORMATION.
without being explicitly EXAMPLES
programmed. INCLUDE
SELF-DRIVING
virtual assistants. CARS AND FACIAL SELF-DRIVING CARS AND FACIAL
Deep Learning uses artificial neural networks with multiple
RECOGNITION
Computer SYSTEMS.
Vision: The ability of computers to understand and layersRECOGNITION
to learn complex patterns SYSTEMS.
from large amounts of
interpret visual information. Examples include self-driving data. This approach used in image recognition, NLP, and
cars and facial recognition systems. speech recognition etc.

CONCERN RELATED TO ARTIFICIAL INTELEGENCE

AI Ethics refers to the ethical principles and guidelines that govern the development and use of artificial intelligence. It ensures that
AI systems are designed and used in a responsible, fair, and beneficial manner.

Bias in AI occurs when AI algorithms are trained on biased data, leading to biased outcomes. This can perpetuate existing societal
inequalities and discrimination.

AI and Job Displacement: Concerns about AI replacing human jobs have arisen. While AI can automate certain tasks, it can also create
new jobs and industries.

AI and Privacy: The collection and use of personal data by AI systems raises privacy concerns. It is important to ensure that data is
collected and used ethically and transparently.

TYPE OF INTELEGENCE
Spatial Visual Intelligence is the ability to perceive the Intrapersonal Intelligence is the ability to understand
visual world in 3D and understand the relationships oneself, including one's own thoughts, feelings, and
between objects. motivations.
Mathematical Logical Intelligence: The ability to think Naturalist Intelligence is the ability to recognize
logically, reason mathematically, and understand natural objects, people who have a deep connection to
numerical symbols and patterns. nature.
Linguistic Intelligence: The ability to process language Musical Intelligence is the ability to perceive, create,
effectively, both in understanding and producing and appreciate music, including recognizing pitch,
written or spoken language. rhythm, and melody.
Interpersonal Intelligence is the ability to interact Kinesthetic Intelligence is the ability to control bodily
effectively with others, understanding their feelings, movements with precision and coordination, often
motivations, and perspectives. associated with athletic or artistic skills.
Existential Intelligence is the ability to ponder deep
questions about life, death, and existence, often
involving religious or spiritual contemplation.

WHAT IS NOT ARTIFICIAL INTELIGENCE

Requires human intervention: AI systems should be able to perform tasks autonomously or with minimal human input.
Lack of complex algorithms: AI often involves sophisticated algorithms that enable machines to learn and solve task.

Artificial means man-made and Intelligence is the ability to perform tasks.

 AI PROJECT CYCLE (13 MARKS)
Project Cycle is a scientifically proven method to tackle problems. It involves an interconnected step-by-step process to ensure
a systematic and effective problem-solving method.

COMPONENTS OF AN AI PROJECT CYCLE ARE COMPONENTS OF AN AI PROJECT CYCLE ARE

Who: Identify all stakeholders directly or indirectly
The 4W's of Problem Scoping 1 Problem Scoping
affected by the problem.
It is a systematic approach to understanding a problem,
What: Define the problem's nature and gather evidence to identifying its root causes, and clearly defining project goals.
support its existence.
Where: Determine the problem's location, context, and 2 Data Acquisition
circumstances. It involves collecting accurate and reliable data for analysis.
Why: Justify the importance of problem and the value of Data features are the specific types of data you'll gather,
addressing it. such as salary amount, increment percentage, increment
period, bonus, and more.
Problem Statement Template helps us to summarize all the
key points into one single template. So that in the future, 3 Data Exploration
whenever there is a need to look back at the basis of the
It is the process of organizing and analyzing data to uncover
problem, we can take a look at the Problem Statement
insights and patterns. It involves transforming raw data into
Template and understand its key elements.
meaningful formats like tables, charts, or databases.
THE STAKE HOLDER WHO
4 Modelling
PROBLEM ISSUE PROBLEM WHAT
It involves creating and evaluating various models based on
When Location WHERE visualized data to identify strengths and weaknesses.
Ideal Solution How Solution will Help WHY
5 Evaluation
DATA SET It is the process of assessing an AI model's capabilities by
Used to train the model. Typically Used to evaluate the model's
inputting test data and comparing its outputs to the expected
constitutes 70-80% of the total performance. Typically constitutes results. Different evaluation techniques exist, depending on
dataset. 20-30% of the total dataset. the model's type and purpose.

Big data Sustainable Development Goals

It refers to datasets that are so large, complex, or diverse that It is the practice of meeting present needs without
traditional data processing methods are inadequate. These datasets compromising the ability of future generations to meet their
often involve unstructured data, which is not organized in a predefined
own needs. The
format. Data Collecting Source:- Web Scraping, Sensors, Camera,
Observation, API, Servey etc. It a set of 17 global targets adopted by all United Nations
Member States in 2015, aim to achieve a more equitable and
Modelling Approach sustainable world by 2030. These goals address a wide range
of issues, including poverty, inequality, climate change, and
A. Rule Based Modeling B. Learning based modelling environmental protection.
It explicitly defines relationships It allows machines to learn from
and patterns within the data. data and improve their performance Learning based modelling
This approach requires the over time. This approach does not
developer to specify rules or
require explicit programming of A. Supervised learning A. Unsupervised Learning
rules.
conditions that the model must It is a machine learning It is a machine learning
follow. Example, labelled images of apples technique where the technique where the
and bananas would indicate which
Example: model trained on images images belong to each category, algorithm is trained on a algorithm learns from
of apples and bananas might be allowing the model to learn to dataset with labelled inputs unlabeled data. There are no
programmed with rules like distinguish between them and corresponding outputs. predefined categories or
"round shape" and "red color" to labels provided to the model.
identify new apple images.
Key points: Labeled data,
Pattern recognition and Key Points: Unlabeled Data,
Prediction. Pattern Discovery and Self-
EXAMPLE OF UNSUPERVISED LEARNING : IMAGINE A
CHILD WATCHING A MAGICIAN PERFORM TRICKS BY Learning.
OBSERVING AND PRACTICING, THE CHILD CAN LEARN TO
PERFORM SIMILAR TRICKS ON THEIR OWN.
 AI PROJECT CYCLE (13 MARKS)
(A) CLASSIFICATION (B) REGRESSION (C) CLUSTERING
Classification is a type of supervised learning where the goal is to categorize data into discrete classes or labels. The model
learns from labelled examples to identify patterns and assign new data points to the appropriate categories (e.g., spam vs. not
spam, cat vs. dog)

Regression is another type of supervised learning where the goal is to predict continuous numerical values. The model learns
from labelled examples to identify relationships between input variables and output variables, allowing it to make predictions
for new data points (e.g., house prices, stock prices, Recommendation systems)

Clustering is an unsupervised machine-learning technique that groups similar data points based on patterns or trends
identified within the data.
Important N O T E S
TOPIC DATE

CUES NOTES

SUMMARY
 iN GH
H iT S 871
R O 873
8 0 0
P - 8
- I
CS