Introduction to Intelligent

Systems

Lecture 1
Email: [email protected]
Course Description

This course provides an intensive introduction to intelligent systems and its

applications to problems of business, transportation, agriculture, education,
tourism, government, medical diagnosis, therapy selection, monitoring and
learning from databases. It covers analysis and design concepts of intelligent
systems.
Course Content

• Intelligent system and problem solving methods

• Search algorithms
• Expert system
• Fuzzy systems
• Neural networks
• Genetic algorithm
• Machine learning
• Prediction, classification and clustering problem solving
• Use of Intelligent system tools – C++, Java, Matlab, Python, etc.
Course Objectives:

The course is designed for the students to:

● Utilize problem solving methods of AI to construct models of systems
● Demonstrate intelligent behavior including dealing with uncertainty, learning
from experience and following problem solving strategies.
● Identify different types of intelligent systems.
● Determine which type of intelligent system techniques would be suitable for
a given type of application problem
● Demonstrate a mini project work of Intelligent Systems for healthcare,
business, transport, agriculture, education, tourism, government using Java,
Python, MatLab, C++ or any other programming Language.
Course Learning Outcomes

After completing the course, the students should be able to:

• Explain the design concept of intelligent systems
• Apply techniques learned to automate systems
• Utilize machine learning concepts and techniques to develop intelligent
systems
Mode of Assessment

Assignment: 10%
Midterm: 20%
Project: 20%
Final Exams: 50%
What are Intelligent Systems?

Definition: Technologies that emulate human intelligence by integrating

capabilities such as sensing, data processing, machine learning, and
decision-making.
Purpose: To enhance efficiency and decision-making in various applications
from daily life to industrial processes.
Why are Intelligent Systems Important?

Automation and Efficiency: Streamline complex processes and reduce human error.
Decision Support: Provide support in critical decision-making scenarios, improving
outcomes in fields like healthcare and finance.
Personalization: Adapt services and products to individual user needs and preferences,
enhancing user experience.

Relevance in Today's World

Pervasive across Industries: From smart homes and autonomous vehicles to advanced
manufacturing and healthcare, intelligent systems are transforming our world.
Impact on Society: Significant effects on lifestyle, employment, and privacy
considerations.
Key Components of Intelligent Systems

Sensors and Data Collection: Devices and software

that gather raw data from the environment or
user interactions. Example: Cameras in
autonomous vehicles, temperature sensors in
smart thermostats, user input through
touchscreens.
Data Processing: Converting raw data into a
format that can be easily analyzed. This includes
cleaning data, sorting, and sometimes
compressing.E.g Filtering noise from sensor
data, organizing data into databases for easy
access.
Machine Learning and Artificial Intelligence:
Algorithms and models that enable systems to
learn from data, improve over time, and make
predictive decisions. Examples:
Recommendation systems in e-commerce,
predictive text in smartphones.
cont..

Decision Making: The capability of

intelligent systems to make autonomous
decisions based on processed data and
learned experiences. Examples: Self-
driving cars deciding when to change
lanes, smart irrigation systems adjusting
water usage based on weather
predictions.
Human-Machine Interaction: Interfaces
that allow users to interact with and
provide feedback to the system, which
in turn adapts to better meet user
needs. Examples: Voice assistants like
Siri and Alexa, interactive dashboards in
business analytics.
Types of Intelligent Systems

Autonomous Vehicles: Vehicles equipped with sensors and AI to navigate roads

and traffic without human intervention.
Smart Home Devices: Devices that automate home functions like lighting,
heating, and security, learning from user habits and preferences.
Healthcare Systems: Systems that analyze medical data to assist in diagnostics,
treatment planning, and patient monitoring.
cont..

Industrial Automation
Use in Manufacturing and production Robots and AI systems that optimize
production processes, improve safety, and reduce operational costs.
Personal Assistants: AI-driven applications that assist with scheduling,
information retrieval, and various personal tasks through voice or text
interaction.
How Intelligent Systems Work

Data Collection: To acquire all necessary inputs that the system will process and
analyze. This is the foundational step where accuracy is crucial. It uses Sensors,
digital interactions, and manual data entries are common sources. For instance,
in autonomous vehicles, cameras and radar collect real-time environmental data.
Data Processing: To transform raw data into a structured format suitable for
analysis. This step involves cleaning data (removing irrelevant or erroneous data),
integrating various data sources, and sometimes compressing data to handle it
more efficiently. Uses techniques like signal processing for sensor data or natural
language processing for text data are applied.
cont..

Learning and Adaptation Purpose: To enable the system to improve its performance over time by
learning from data. This is where the system starts to 'understand' and 'adapt' based on historical
data. Machine learning algorithms are used, ranging from supervised learning (learning from labeled
data) to unsupervised learning (detecting patterns in data without pre-assigned labels) and
reinforcement learning (learning based on the outcome of decisions).
Autonomous Decision Making: Purpose: To make decisions automatically, based on the insights
gained from data and learning processes. This step demonstrates the system’s capability to operate
independently. Decision algorithms analyze the learned data and current inputs to choose the best
action according to predefined criteria. For example, a smart thermostat may decide to lower the
heating based on the time of day and the ambient temperature.
Interaction and Feedback: To maintain a loop of communication between the system and its users,
allowing the system to receive feedback and refine its operations. User interfaces allow for input
that the system can use to fine-tune its performance. Feedback mechanisms can be direct (user
adjustments to the system settings) or indirect (analysis of user behavior patterns).
Benefits of Intelligent Systems

● Enhanced Efficiency

● Improved Accuracy

● Personalization

● Cost Reduction

● Decision Support
We are in an engineering context
• We are not interested in deciding whether a system is intelligent or not

• We are interested in having tools for systems engineers

Tools like design metaphors, Engineers who need to

architectural patterns, conceive, analyze, design and
computational methods and program efficiently intelligent
software tools systems

2
How can we characterize an intelligent system?

We can distinguish three main properties:

1. Working in a complex world
2. Primary cognitive abilities (e.g., perception, language use, etc.)
3. Complex intelligent behavior (e.g., rationality, learning, etc.)

3
How can we characterize an intelligent system?

We can distinguish three main properties:

1. Working in a complex world
2. Primary cognitive abilities (e.g., perception, language use, etc.)
3. Complex intelligent behavior (e.g., rationality, learning, etc.)

4
Property 1: Working in a complex world

• An intelligent system operates in an environment and interacts with other agents

(a user or other individuals)
• The system observes features from the environment through sensors and
performs actions using actuators
• The use of sensors and actuators (real or virtual) separates the body of the
intelligent system from the rest of the environment (“embodiment”)

Sense
Sensors

Intelligent Communicate
Environment system Other agents

Actuators

Act

5
Other examples

Observable Performance
System Environment User Actions
features measure

Images from Steering, Safety, travel

Roads, cars, cameras, accelerator, time, comfort,
Self-driving car Passenger
pedestrians, … coordinates from brake, signal, fuel
GPS, speed horn consumption

Medical Test results, Drug Health, costs

diagnosis Patients Physician medical history, prescriptions, of tests and
system etc. proposed tests treatment

Tests,
proposed
Chemistry Chemistry Answers given by Student’s
Instructor exercises,
tutor system students students score on tests
proposed
readings

7
There are different properties that define the complexity
of the environment with respect to the system
• Static / dynamic [Russell, Norvig, 2009]
The environment (doesn’t change / changes) while an
agent is deliberating

• Discrete / continuous
The state of the environment, time, percepts or actions
(are discrete / are continuous) Sense

• Fully-observable / partial-observable
Sensors (detect / don’t detect) all aspects that are
relevant to the choice of action
Intelligent
• Deterministic / stochastic Environment system
The next state of the environment (is / isn’t) completely
determined by the current state and the action

• Episodic / sequential
Actions (don’t influence / influence) future actions Act

• Known / unknown
The outcomes for actions (are known / are not
known) by the agent in advance

Russell, S., Norvig P. (2009). Artificial Intelligence: A Modern Approach (3rd edition). Pearsons Education Limited. 8
Example: Environment of a chess player

Chess player

• Static / dynamic
• Discrete / continuous
• Fully-observable / partial-observable
• Deterministic / stochastic
• Episodic / sequential
• Known / unknown

9
Example: Environment of a self-driving car

Self-driving car

• Static / dynamic
• Discrete / continuous
• Fully-observable / partial-observable
• Deterministic / stochastic
• Episodic / sequential
• Known / unknown

10
How can we characterize an intelligent system?
We can distinguish three main properties:
1. Working in a complex world
2. Primary cognitive abilities (e.g., perception, language use, etc.)
3. Complex intelligent behavior (e.g., rationality, learning, etc.)

11
We can identify multiple cognitive abilities
1993
Cognitive ability:
Ability that requires to process mental information

John B. Carroll
Professor of Psychology
University of Chicago
(1920 -2003)

Carroll, J. B. (1993). Human cognitive abilities: A survey of factor-analytic studies. Cambridge

University Press. 12
We follow a pragmatic engineering approach
to identify cognitive abilities
• We identify abilities that:
– Are common in computer systems
– Can be implemented with AI methods
• We consider two separated levels:
– Primary abilities (basic abilities)
– Secondary abilities (abilities that use models of other abilities)

13
Property 2: Primary cognitive abilities

Other agents

Interaction with other

Interaction agents (e.g., using
Reasoning about the language)
world and making
decisions about Deliberation
what to do
Action
Perception
control

Extraction of relevant
data from the Control the
observed world Environment
execution of the
own actions

14
Example: Autonomous car

Passenger

Interaction
(Passenger requests destination)

Deliberation
(Path planning to reach the requested destination)
Perception Action control

Pedes- Traffic Accele-

Vehicles Steering Braking
trians signals ration

Data extraction
Control of
from ultrasonic
driving
sensors, radar, lidar,
mechanisms
camera and GPS Environment
15
The gap between deliberation and
perception-actuation requires specific abilities

Other agents

Interaction

Deliberation

Attention Symbol Execution Cognizant

Gap mechanisms grounding control failure

Perception Action control

P1 P2 A1 A2
An
Pm

Environment

17
“Action control” provides “reactive behavior”

Deliberation
Other agents
Making decisions about what to do based on justifiable
reasons

Advantages:
Interaction
• Reactive behaviors can be inhibited to reach more useful
long-term goals
• Decisions are consistent with own knowledge
Deliberation

Action
Reactive behavior
Perception
control
Generation of instantaneous actions in response to a
stimulus (e.g., animal reflexes or in decisions based on
Environment
intuitions).

Advantage:
• Efficient reaction to dynamic events in a dynamic
environment (it uses limited memory about the world)
18
We can distinguish two types of systems
according to who acts in the environment

Autonomous system Advisor system

• Acts in the environment to help the user • Helps the user to act in the environment
• The system makes decisions about what to do • The user makes decisions about what to do

Perform Help me
task T perform
for me task T
Sense Intelligent Sense Intelligent
autonomous advisor
Environ- Completion Environ- system
system Suggestion
ment User User
ment

Act Act

(a) (b)

19
An intelligent system may interact with other system

Sense Sense

Reques
Intelligent t
Intelligent
Environ- system Answer system Environ-
ment 1 1 2 ment 2
Act

Act

20
Intelligent systems can be part of
multiagent systems creating complex organizations
Communicate

Communicate

Communicate Communicate Communicate Communicate

Agent Agent Agent Agent Agent

Sense Sense Sense Sense Sense

and act and act and act and act and act

Partial Partial Partial Partial Partial

environment environment environment environment environment

Global environment
21
How can we characterize an intelligent system?
We can distinguish three main properties:
1. Working in a complex world
2. Primary cognitive abilities (e.g., perception, language use, etc.)
3. Complex intelligent behavior (e.g., rationality, learning, etc.)

22
Property 3: Complex intelligent behavior

Other agents

Interaction

Deliberation

Action
1. Acting rationally Perception
control
2. Adaptation through learning
3. Introspection
Environment

23
Sub-property 3.1: Acting rationally
A system acts rationally if it makes decisions to obtain the maximum
performance measure

Examples:
• A chess player selects the movement that maximizes the expectation of
winning the game
• A self-driving car selects the best route to reach a destination considering
possible traffic jams

Implementation:
• The expected performance measure of actions is usually uncertain
• Rational behavior can be explicitly programmed using algorithms from
decision theory (with a probabilistic representation)

24
Rational decisions affect different cognitive abilities

Other agents

What is the right

What is the next
action to do?, what is
question to ask the
the right method to
user?, … Interaction perform a task?, …

Deliberation

Action
Perception
control
What part of the What is the right
environment requires method to control an
more attention?, … action?, …
Environment

25
Sub-property 3.2: Adaptation through learning
The system is capable of improving its performance over multiple interactions
with the world

Examples:
• A chess player improves its capacity to win by learning from game
experience
• A self-driving car reduces the time to reach destination in a city by learning
from the experience of urban trips

26
Adaptation through learning can affect
different cognitive abilities

Other agents

Learning by
Learning user
deduction using a
preferences, …
Interaction world model, …

Deliberation

Action
Perception
control Improving action
Learning
control by
relevance of
learning (object
features, …
manipulation, …)
Environment

27
Sub-property 3.3: Introspection
• Capacity to analyze one's cognitive abilities
– The system uses an observable model of its own abilities
– This model is used to simulate self-awareness processes

Practical utility:
• Allows the system to judge its own actions
– This provides feedback to be able to learn
(this feedback can also be done by simulating reactive feelings)
• Allows the system to generate explanations
– E.g., the system is able to justify recommended decisions to the user

28
Summary of properties of an intelligent system

1. Working in a complex Other agents

– Environment
world
– Other agents (e.g., user)
Intelligent
2. Primary cognitive system
Interaction
abilities
– Perception
– Action control • Acting rationally
Deliberation • Adaptation through learning
– Deliberation • Introspection

– Interaction Perception
Action
control
3. Complex intelligent
– Acting rationally
behavior
Environment
– Adaptation through learning
– Introspection

29
END