Unit I

Introduction
to Artificial
Intelligence
Dr. Praveen Kumar Loharkar
Artificial Intelligence (AI): Definition

• Artificial Intelligence (AI) refers to the simulation of

human intelligence in machines capable of performing
tasks that typically require human cognitive abilities.

• These tasks include learning, reasoning, problem-solving,

perception, and language understanding.

• AI systems can analyze data, adapt to new information, and

make decisions based on patterns and rules.
Reference:
•Russell, S. J., & Norvig, P. (2022). Artificial Intelligence: A Modern Approach (4th ed.).
What are the Applications of
Artificial Intelligence?
 Artificial
Intelligence:
Applications
Finance and Banking:
• Risk Assessment: AI models analyze
historical data to assess credit risk,
detect fraudulent transactions, and
prevent financial crimes.
• Algorithmic Trading: AI algorithms
predict market trends and optimize
trading strategies.
• Customer Service: Chatbots handle
routine inquiries, resolve issues, and
improve customer experience.
• Personalized Financial Advice: AI
recommends investment portfolios based
on individual goals and risk tolerance.
Artificial
Intelligence:
Healthcare:
Applications
• Precision Medicine: AI analyzes patient
data (genetic, clinical, lifestyle) to
personalize treatment plans and predict
disease risks.
• Medical Imaging: AI enhances image
quality, automates diagnosis, and assists
radiologists in interpreting CT and MRI
scans.
• Drug Discovery: AI accelerates drug
development by predicting molecular
interactions and identifying potential
compounds.
• Virtual Health Assistants: AI-powered
chatbots provide medical information,
appointment scheduling, and symptom
Artificial
Intelligence:
Applications
Transportation and Logistics:
• Route Optimization: AI optimizes
delivery routes, reducing fuel
consumption and delivery time.
• Autonomous Vehicles: AI enables self-
driving cars and trucks, enhancing safety
and efficiency.
• Traffic Management: AI monitors traffic
flow, predicts congestion, and adjusts
signals for smoother transportation.
• Smart Parking: AI guides drivers to
available parking spaces, reducing
congestion and emissions.
 Modeling

• Definition: Modeling involves creating a representation (model) of a real-

world phenomenon or system.
• In AI, models capture relationships, patterns, and behaviours.
• Types of Models:
• Statistical Models: These use statistical techniques to describe data and
make predictions (e.g., linear regression, decision trees).
• Machine Learning Models: These learn from data and adapt over time
(e.g., neural networks, support vector machines).
• Symbolic Models: These represent knowledge using symbols and rules
(e.g., expert systems).
 Model Creation Process

• Data Collection: Gather relevant data (e.g., images, text, sensor

readings).
• Feature Extraction: Identify relevant features (attributes) from the
data.
• Model Selection: Choose an appropriate model type based on the
problem.
• Training: Use labeled data to adjust model parameters (weights)
through optimization algorithms.
• Validation: Evaluate the model’s performance on unseen data.
• Deployment: Deploy the trained model for real-world use.
 Inference

• Definition: Inference refers to drawing conclusions or making

predictions based on evidence or existing knowledge.
• Inference in AI:
• Probabilistic Inference: Using probability distributions to
reason about uncertainty (e.g., Bayesian networks).
• Logical Inference: Applying logical rules to deduce new
information (e.g., rule-based systems).
• Statistical Inference: Making predictions based on observed
data (e.g., regression, hypothesis testing).
 Learning

• Supervised Learning: The model learns from labeled examples

(input-output pairs). It generalizes to unseen data.

• Unsupervised Learning: The model discovers patterns in unlabeled

data (e.g., clustering, dimensionality reduction).

• Reinforcement Learning: The model learns by interacting with an

environment and receiving rewards or penalties.

• Transfer Learning: Leveraging pre-trained models for new tasks by

fine-tuning them on specific data.
 A B

ThePhoto by PhotoAuthor is licensed under CCBYSA.

C ThePhoto by PhotoAuthor is licensed under CCBYSA.

ThePhoto by PhotoAuthor is licensed under CCBYSA. ThePhoto by PhotoAuthor is licensed under CCBYSA.
 AI v/s Machine Learning v/s Deep
Learning
Machine Learning (ML):
• ML is a subfield of AI. It involves training algorithms on data to create adaptable models
that can perform various complex tasks without explicit programming.

Key characteristics of ML:

• Subset of AI: ML is a subset of AI, focusing on automatic adaptation with minimal human
intervention.

• Data-Driven Learning: ML models learn from historical data and generalize patterns to
make predictions or decisions.

• Linear/Simple Correlations: ML often deals with simpler, linear relationships between

input features and output predictions.

• Training on Smaller Data Sets: ML models can work with smaller datasets compared to
 AI v/s Machine Learning v/s Deep
Deep Learning
Learning (DL)
• Deep learning is a specialized form of ML that leverages deep neural networks
(multilayered architectures) to simulate the decision-making power of the human brain.
• Key characteristics of deep learning:
• Subset of ML: Deep learning is a subset of ML, specifically focusing on neural networks with
multiple layers.
• Complex Correlations: Deep learning models can capture non-linear, complex relationships
in data.
• Large Amounts of Data: Deep learning requires extensive data for training.
• Higher Accuracy: Although training takes longer, deep learning models achieve higher
accuracy.
• Specialized Hardware (GPUs): Deep learning models benefit from specialized GPUs for
efficient training.
• Deep learning is a powerful tool within the broader landscape of AI and ML.
AI v/s Machine Learning v/s Deep
Learning

ThePhoto by PhotoAuthor is licensed under CCYYSA.

 Intelligent Agents
• What is an Agent?
• An agent can be anything that perceive its environment through
sensors and act upon that environment through actuators.
• An Agent runs in the cycle of perceiving, thinking, and acting.
• Sensor: Sensor is a device which detects the change in the
environment and sends the information to other electronic devices. An
agent observes its environment through sensors.
• Actuators: Actuators are the component of machines that converts
energy into motion. The actuators are only responsible for moving
and controlling a system. An actuator can be an electric motor,
gears, rails, etc.
• Effectors: Effectors are the devices which affect the environment.
Effectors can be legs, wheels, arms, fingers, wings, fins, and
display screen.
 Intelligent Agents

• An agent can be:

• Human-Agent: A human agent has eyes, ears, and other organs
which work for sensors and hand, legs, vocal tract work for
actuators.
• Robotic Agent: A robotic agent can have cameras, infrared range
finder, NLP for sensors and various motors for actuators.
• Software Agent: Software agent can have keystrokes, file contents
as sensory input and act on those inputs and display output on the
screen.
 Intelligent Agents

Intelligent Agents:
• An intelligent agent is an autonomous entity which act upon an
environment using sensors and actuators for achieving goals.
• An intelligent agent may learn from the environment to achieve their
goals. A thermostat is an example of an intelligent agent.
Following are the main four rules for an AI agent:
• Rule 1: An AI agent must have the ability to perceive the
environment.
• Rule 2: The observation must be used to make decisions.
• Rule 3: Decision should result in an action.
• Rule 4: The action taken by an AI agent must be a rational action.
Concept of Rationality
Rationality:
The rationality of an agent is measured by its performance metrics.
Rationality can be judged on the basis of following points:
• Performance measure/metrics which defines the success criterion.
• Agent’s prior knowledge of its environment.
• Best possible actions that an agent can perform.
• The sequence of percepts (a percept refers to the input that an
intelligent agent perceives at any given moment).
• Examples of percepts include inputs from touch sensors, cameras, infrared
sensors, sonar, microphones, mice, and keyboards.
• These percepts can also represent higher-level features like lines, depth,
objects, faces, or gestures.
Structure of Agents

• The task of AI is to design an agent program which implements the

agent function.
• The structure of an intelligent agent is a combination of architecture
and agent program. It can be viewed as:
Agent = Architecture + Agent program
Important Terms:
• Architecture: Architecture is machinery that an AI agent executes on.
• Agent Function: Agent function is used to map a percept to an action.
• Agent program: Agent program is an implementation of agent
function. An agent program executes on the physical architecture to
produce function f.
 Structure of Agents

Examples:
• Architecture: An autonomous robot’s architecture includes its sensors (such as
cameras, lidar, or microphones), actuators (such as motors or wheels), and the
computational resources (such as CPUs or GPUs) that process information and execute
actions.
• Agent Function: Agent function is used to map a percept to an action.
f:P* → A
where:
• (f) is the agent function.
• (P*) represents the set of all possible percepts.
• (A) represents the set of all possible actions.
Agent program: Consider an AI chatbot. Its agent program processes user messages
(percepts) and generates appropriate responses (actions) based on predefined
rules, machine learning models, or other algorithms.
PEAS Representation

• PEAS is a type of model on which an AI agent works upon.

• When we define an AI agent or rational agent, then we can group its
properties under PEAS representation model. It is made up of four
words:
• P: Performance measure
• E: Environment
• A: Actuators
• S: Sensors
• Here performance measure is the objective for the success of an agent's
behavior.
PEAS Representation

For a self-driving car then PEAS representation will be:

• Performance: Safety, time, legal drive, comfort
• Environment: Roads, other vehicles, road signs, pedestrian
• Actuators: Steering, accelerator, brake, signal, horn
• Sensors: Camera, GPS, speedometer, odometer, accelerometer, sonar.