Computer (Class – 10th)

Deepak Chandel
What is intelligence?
 Intelligence is derived from Latin word ‘Intelligo’.
 Capacity to learn, understand, and apply knowledge.
 Helps in problem-solving, adapting to new situations,
and interpreting complex information.
Types of Intelligence
1. Logical-Mathematical: Analytical and quantitative
problem-solving
2. Linguistic: Language skills and expression
3. Spatial: Visual and spatial awareness
4. Musical: Sensitivity to sound, rhythm, and melody
5. Intrapersonal: Self-awareness and self-regulation
6. Interpersonal: Understanding and interacting with
others
Types of Intelligence (conti…)
7. Naturalistic: Recognizing and categorizing natural
phenomena
8. Bodily-Kinesthetic: Physical movement and
coordination
9. Emotional Intelligence: Recognizing, understanding,
and managing emotions
10. Social Intelligence: Building relationships and
managing conflicts
11. Creative Intelligence: thinking outside the box, and
come up with innovative solutions to problems
12. Existential Intelligence: religious and spiritual
awareness
Traits of intelligence
1. Curiosity
 Strong desire to learn and explore new ideas
 Willingness to question and seek deeper understanding
2. Adaptability
 Flexibility in thinking and behavior
 Ability to adjust to new situations and solve problems on
the go
3. Problem-Solving Skills
 Logical and structured approach to overcoming challenges
 Ability to analyze situations and find effective solutions
Traits of intelligence (conti…)
4. Self-Awareness
 Understanding one’s own strengths and weaknesses
 Recognizing one’s own emotions and reactions, especially
under stress
5. Critical/Abstract Thinking
 Ability to think beyond concrete concepts
 Skill in identifying patterns, making connections, and
imagining possibilities
6. Empathy
 Ability to understand and relate to the feelings and
perspectives of others
 Vital component of emotional intelligence
Traits of intelligence (conti…)
7. Reasoning
 Analyzing information objectively and making reasoned judgments
 Skill in questioning assumptions and evaluating evidence
8. Creativity
 Generating unique ideas and novel solutions to problems
 Thinking outside the box and embracing original concepts
9. Learning Ability
 Strong learning capacity
 Continuously improve their understanding and performance
10. Good Memory
 Ability to retain and recall information effectively
 Important for both short-term learning and long-term knowledge
retention
Artificial Intelligence (AI)
 field of computer science focused on creating
machines or software that can perform tasks typically
requiring human intelligence.
 includes abilities such as learning from experience,
recognizing patterns, making decisions,
understanding natural language, and solving complex
problems.
 AI enables computers to think and act in ways that
mimic human cognition and behavior, allowing them
to process information, understand it, and respond
intelligently.
History of AI
 1941 – Initial computer, even to run a single program
they need to do many connection and it is used to be a
complex task to do
 1943 – First work recognized by Warren McCulloh &
Walter Pits. Proposed a model of AI neurons.
 1949 – Donald Hebb updated & modified connection
strength b/w neurons called Hebbian learning.
 1950 – Allen Turing proposed a test “computing
machinery and intelligence”
 1956 – Darth Mouth Conference adopted the word AI
by John McCarthy.
History of AI
 1966 – Joseph Weizen Baum developed first chatbot
“ELIZA”
 1972 – First intelligent humanoid robot – WABOT-1 made
in Japan.
 (1974 - 1980 winter)
 1980 – AI comeback with expert system, they are
programmed with decision making abilities.
 (1987 – 1993 second AI winter)
 1997 – IBM deep blue defeated chess champion Garry
Casparov.
 2002 – AI entered in the home in form of Roomba, a
vacuum cleaner.
History of AI
 2006 – AI in business world, company like FB, Twitter.
 2011 – IBM Watson won jeopardy (a quiz show), it can
solve complex question & riddles.
 2012 – Google launched Android app “Google Now”
which provide information to user as a prediction.
 2014 – chatbot “Eugene Goostman” won a competition
in the famous turing test.
AI vs ML vs Dl
Artificial Intelligence
AI refers to the science and engineering of making
intelligent machines, especially intelligent computer
programs.

CAT

DOG
Machine Learning
Machine learning (ML) is a subfield of artificial intelligence (AI)
that focuses on using data and algorithms to enable machines to
learn from experience and perform tasks without explicit
programming.

Features –
a. Eyes CAT
b. Nose
c. Shape
d. Claws
e. Size DOG
f. Teeth
Deep Learning
Deep learning is a subset of machine learning that utilizes
multilayered neural networks, known as deep neural networks,
to simulate the complex decision-making processes of the
human brain.

CAT/DOG
Definitions of AI
 Stanford University – the science and engineering of
making intelligent machines, especially intelligent
computer programs.
 IBM – the science of training systems to emulate
human tasks through learning and automation.
 MIT – field of computer science that focuses on
creating computer systems capable of performing
tasks that would typically require human intelligence.
 Elon Musk – Digital intelligence that is greater then
the smartest human on earth across almost all
dimensions.
Scope/Applications of AI
 Healthcare -
 Autonomous Vehicles –
 Robotics and Automation –
 Natural Language Processing and Virtual assistant –
 Financial Services –
 Personalized Learning and Education –
 Sustainability and Environmental Applications –
 E-commerce & Recommendation System
 Cyber Security
 Gaming
 Manufacturing & Supply Chain Management
Future of AI
 Improved Safety -
 Efficient Traffic Management –
 Enhanced Accessibility –
 Sustainable and Eco Friendly Solutions –
 Mobility as a Service –
 Delivery and Logistics –
Intelligent Agent
 Intelligent Agent refers to a software that can perceive
its environment, analyze information, make decision
and take action to achieve specific goals.
 Designed to exhibit intelligent behavior by utilizing
algorithms, knowledge and reasoning capabilities.
Intelligent Agent
 The design of an intelligent agent typically involves four key components:
1. Perception: Agents have sensors or mechanisms to observe and perceive
aspects of their environment. This may involve collecting data from the
physical world, accessing databases, or receiving input from other software
components.
2. Reasoning: Agents possess computational or cognitive capabilities to
process the information they perceive. They use algorithms, logic, or
machine learning techniques to analyze data, make inferences, and derive
insights from the available information.
3. Decision-Making: Based on their perception and reasoning, agents make
decisions about the actions they should take to achieve their goals. These
decisions are guided by predefined objectives, which may include optimizing
certain criteria or satisfying specific constraints.
4. Action: Agents execute actions in their environment to affect change and
progress towards their goals. These actions can range from simple
operations, such as sending a message or adjusting parameters, to more
complex tasks, such as navigating a virtual world or controlling physical
devices.
How Intelligent Agent work
Inside?
How Intelligent Agent work
Inside?
1. Environment: Environment is the area around the agent that it
interacts with. An environment can be anything like a physical space,
a room or a virtual space like a game world or the internet.
2. Sensors: Sensors are tools that AI agent uses to perceive their
environment. They can be any physical like cameras, microphones,
temperature sensors or a software sensor that read data from files.
3. Actuators: Actuators are tools that AI agent uses to interact with
their environment through some actions. They can be any physical
actuators like wheels, motors, robotic hands, or computer screens or
they can be software actuators that send messages.
4. Effectors: Effectors take instructions from decision making
mechanism and translates them into actions and these actions are
performed through actuators.
PEAS Representation of AI agent
 Performance measure: Performance measure is a criteria that measures the success of
the agent. It is used to evaluate how well the agent is achieving its goal.
For example, in a spam filter system, the performance measure could be minimizing the
number of spam emails reaching the inbox.
 Environment: The environment represents the domain or context in which the agent
operates and interacts. This can range from physical spaces like rooms to virtual
environments such as game worlds or online platforms like the internet.
 Actuators: Actuators are the mechanisms through which the AI agent performs actions
or interacts with its environment to achieve its goals. These can include physical
actuators like motors and robotic hands, as well as digital actuators like computer screens
and text-to-speech converters.
 Sensors: Sensors enable the AI agent to gather information from its environment,
providing data that informs its decision-making process and actions. These sensors can
capture various environmental parameters such as temperature, sound, movement, or
visual input. Examples of sensors include cameras, microphones, temperature sensors,
and motion sensors.
Applications of Intelligent Agents
1. Autonomous Systems: Intelligent agents power autonomous vehicles,
drones, and robots, enabling them to perceive their surroundings,
navigate complex environments, and make decisions in real-time.
2. Personal Assistants: Virtual personal assistants like Siri, Alexa, and
Google Assistant employ intelligent agents to understand user queries,
retrieve relevant information, and perform tasks such as scheduling
appointments, setting reminders, and controlling smart home devices.
3. Recommendation Systems: E-commerce platforms, streaming
services, and social media platforms utilize intelligent agents to analyze
user preferences and behavior, providing personalized recommendations
for products, movies, music, and content.
4. Financial Trading: Intelligent agents are employed in algorithmic
trading systems to analyze market data, identify trading opportunities,
and execute trades autonomously, maximizing returns and minimizing
risks.
Use of AI in Problem Solving with example
 Data Collection – gathers large volume of historical
transaction data, including legitimate and fraudulent
transactions. Data serves as a training set for the AI
model.
 Feature extraction – Al system extracts relevant
features from the transaction data, such as amount,
location, time and customer behavior pattern.
 Machine Learning Model – AI system trains a model
on the collected data. Model learns from pattern.
Use of AI in Problem Solving with example
 Real time monitoring – When model is trained, it is
deployed in real time to analyze incoming
transactions. Each new transaction is evaluated based
on the learned patterns and features.
 Anomaly Detection – AI model compares the features
of each transaction with the learned patterns. It raises
an alert when found abnormal transaction.
 Continuous Learning – AI system continuously
updates its model based on new data and feedback
from human experts.