Unit I

IntroductIon:
Artificial Intelligence is concerned with the design of intelligence in an artificial device.
The term was coined by John McCarthy in 1956.
Intelligence is the ability to acquire, understand and apply the knowledge to achieve
Goals in the world.
AI is the study of the mental faculties through the use of computational models
AI is the study of intellectual/mental processes as computational processes.

AI program will demonstrate a high level of intelligence to a degree that equals
or exceeds the intelligence required of a human in performing some tasks.
AI is unique, sharing borders with Mathematics, Computer Science,
Philosophy, Psychology, Biology, Cognitive Science and many others.
Although there is no clear definition of AI or even Intelligence, it can be described as an
attempt to build machines that like humans can think and act, able to learn and use
knowledge to solve problems on their own.’

The definitions of AI:

Applications of AI:
AI algorithms have attracted close attention of researchers and have also been applied
successfully to solve problems in engineering. Nevertheless, for large and complex
problems, AI
algorithms consume considerable computation time due to stochastic feature of the search
approaches
1. Business; financial strategies

2. Engineering: check design, offer suggestions to create new product, expert systems for
all engineering problems
3. Manufacturing: assembly, inspection and maintenance
4. Medicine: monitoring, diagnosing
5. Education: in teaching
6. Fraud detection
7. Object identification
8. Information retrieval
9. Space shuttle scheduling

Artificial Intelligence Techniques

The field of AI has evolved rapidly, giving rise to various techniques that have
transformed how we interact with technology. Let's explore some of the most
prominent AI techniques:

1. Machine Learning
Machine Learning (ML) is one of AI's foundational pillars. This technique
empowers computers to learn from data and improve their performance with
time without explicit programming. ML models can make accurate
predictions and decisions through supervised and unsupervised learning,
impacting everything from personalized recommendations to fraud detection.

2. Natural Language Processing

Natural Language Processing (NLP) allows machines to comprehend,
interpret, and generate human language. This AI technique has paved the way
 for virtual assistants, chatbots, and language translation tools, making
communication between humans and machines more seamless than ever.

3. Computer Vision
Computer Vision equips machines with the ability to interpret visual
information from the world. This technique has revolutionized industries like
healthcare, automotive, and robotics, enabling tasks such as facial
recognition, object detection, and autonomous driving.

4. Deep Learning
Deep Learning takes ML to a higher level by employing neural networks with
multiple layers to process complex data representations. It has propelled AI
achievements, such as beating human champions in games like chess and go
and enhancing image and speech recognition systems.

Natural Language Processing: NLP - NLP is the branch of computer science focused on developing
systems that allow computers to communicate with people using everyday language. It is also called
Computa onal Linguis cs. - NLP is a sub field of AI which deals with the methods of communica ng
with a computer in once on natural language. It includes understanding and genera on as well as
other task such as mul lingual transla on. - Natural languages are used by humans for
communica on. They are dis nctly different from formal languages, such as C++, Java, and PROLOG
because they are not ambiguous. - A system that can work with one human language cannot
necessarily deal with any other human language. Advantages of NLP: NLP minimizes many hardships
a person’s faces while communica ng with the computer. 1) One need not be a computer literate to
communicate with it. 2) One can dispose of special query languages like SQL, which presently
humans use to access informa on from databases.

What Is the Turing Test?

The Turing Test is a deceptively simple method of determining whether a

machine can demonstrate human intelligence: If a machine can engage in
a conversation with a human without being detected as a machine, it has
demonstrated human intelligence.The Turing Test was proposed in a
paper published in 1950 by mathematician and computing pioneer Alan
Turing. It has become a fundamental motivator in the theory and
development of artificial Intelligence (AI).1

Stanford Encyclopaedia of Philosophy. "The Turing Test."

KEY TAKEAWAYS

 The Turing Test measures the intelligence of a test subject to

determine whether a machine can demonstrate intelligence.
 According to the test, a computer program can think if its responses
can fool a human into believing it, too, is human.
 Not everyone accepts the validity of the Turing Test, but passing it
remains a major challenge to developers of artificial intelligence.
 There are variations to the Turing test as well as modifications to the
approach of asking questions in different AI tests.
 The Turing test has several limitations including requiring a
controlled environment, not having a dedicated definition of
intelligence, and needing to adapt to evolving technological
advancements.

Turing Test: Act Human-Like

a. The art of creating machines that perform functions requiring intelligence when
performed by people; that it is the study of, how to make computers do things which, at
the moment, people do better.
b. Focus is on action, and not intelligent behaviour centered around the representation of
the world
c. Example: Turing Test
o 3 rooms contain: a person, a computer and an interrogator.

o the interrogator can communicate with the other 2 by teletype (to

avoid the machine imitate the appearance of voice of the person)
o the interrogator tries to determine which the person is and which

the machine is.7

o The machine tries to fool the interrogator to believe that it is the

human, and the person also tries to convince the interrogator that it is
the human.
o If the machine succeeds in fooling the interrogator, then conclude that

the machine is intelligent.

Intelligent Systems:
In order to design intelligent systems, it is important to categorize them into four
categories (Luger and Stubberfield 1993), (Russell and Norvig, 2003)
1. Systems that think like humans
2. Systems that think rationally
3. Systems that behave like humans
4. Systems that behave rationally

Cognitive Science: Think Human-Like

a. Requires a model for human cognition. Precise enough models
allow simulation by computers.
b. Focus is not just on behaviour and I/O, but looks like reasoning process.
c. Goal is not just to produce human-like behaviour but to produce a sequence of steps of
the reasoning process, similar to the steps followed by a human in solving the same task.
Laws of thought: Think Rationally
a. The study of mental faculties through the use of computational models; that it is,
the study of computations that make it possible to perceive reason and act.
b. Focus is on inference mechanisms that are probably correct and guarantee an optimal
solution.
c. Goal is to formalize the reasoning process as a system of logical rules and procedures

of inference.
d. Develop systems of representation to allow inferences to be like
“Socrates is a man. All men are mortal. Therefore, Socrates is mortal”

Turing Test: Act Human-Like

a. The art of creating machines that perform functions requiring intelligence when
performed by people; that it is the study of, how to make computers do things which, at
the moment, people do better.
b. Focus is on action, and not intelligent behaviour cantered around the representation of
the world
c. Example: Turing Test
o 3 rooms contain: a person, a computer and an interrogator.
o The interrogator can communicate with the other 2 by teletype (to

avoid the machine imitate the appearance of voice of the person)

o The interrogator tries to determine which the person is and which

the machine is.7

o The machine tries to fool the interrogator to believe that it is the

human, and the person also tries to convince the interrogator that it is
the human.
o If the machine succeeds in fooling the interrogator, then conclude that

the machine is intelligent.

Rational agent: Act Rationally

a. Tries to explain and emulate intelligent behaviour in terms of computational process;

that it is concerned with the automation of the intelligence.
b. Focus is on systems that act sufficiently if not optimally in all situations.
c. Goal is to develop systems that are rational and sufficient

Agents and Environments:

Fig 2.1: Agents and Environments

Agent:
An Agent is anything that can be viewed as perceiving its environment through sensors
and acting upon that environment through actuators.

A human agent has eyes, ears, and other organs for sensors and hands, legs,
mouth, and other body parts for actuators.
A robotic agent might have cameras and infrared range finders for sensors
and various motors for actuators.
A software agent receives keystrokes, file contents, and network packets as8
sensory inputs and acts on the environment by displaying on the screen, writing
files, and sending network packets.

Percept:
We use the term percept to refer to the agent's perceptual inputs at any given instant.
Percept Sequence:
An agent's percept sequence is the complete history of everything the agent has ever
perceived.
Agent function:
Mathematically speaking, we say that an agent's behaviour is described by the agent
function that maps any given percept sequence to an action.

Agent program
Internally, the agent function for an artificial agent will be implemented by an agent
program. It is important to keep these two ideas distinct. The agent function is an
abstract
mathematical description; the agent program is a concrete implementation, running on
the agent architecture.
To illustrate these ideas, we will use a very simple example-the vacuum-cleaner world
shown in
Fig 2.1.5. This particular world has just two locations: squares A and B. The vacuum agent
perceives which square it is in and whether there is dirt in the square. It can choose to move
left, move right, suck up the dirt, or do nothing. One very simple agent function is the
following: if the current square is dirty, then suck, otherwise move to the other square. A
partial tabulation of this agent function is shown in Fig 2.1.6.

fig 2.1.5: A vacuum-cleaner world with just two loca ons.

Agent func on
Fig 2.1.6: Partial tabulation of a simple agent function for the example: vacuum-cleaner
world shown in the
Fig2.1.5

Fig 2.1.6(i): The REFLEX-VACCUM-AGENT program is invoked for each new percept
(location, status) and returns an action each time

A Rational agent is one that does the right thing. we say that the right action is the
one that
will cause the agent to be most successful. That leaves us with the problem of deciding how
and when to evaluate the agent's success.
We use the term performance measure for the how—the criteria that determine how
successful an agent is.
Ex-Agent cleaning the dirty floor
Performance Measure-Amount of dirt collected
When to measure-Weekly for better results
What is rational at any given time depends on four things:
The performance measure defining the criterion of success
The agent’s prior knowledge of the environment
The actions that the agent can perform
The agent’s percept sequence up to now.

STRUCTURE OF INTELLIGENT AGENTS

The job of AI is to design the agent program: a function that implements the agent
mapping from precepts to actions. We assume this program will run on some sort of
ARCHITECTURE
computing device, which we will call the architecture.
The architecture might be a plain computer, or it might include special-purpose
hardware for certain tasks, such as processing camera images or filtering audio input. It
might also include software that provides a degree of insulation between the raw computer
and the agent program, so that we can program at a higher level. In general, the
architecture makes the precepts from the sensors available to the program, runs the
program, and feeds the program's action choices to the effectors as they are generated.
The relationship among agents, architectures, and programs can be summed up as
follows: agent = architecture + program

Types of agents:

Agents can be grouped into four classes based on their degree of perceived intelligence and
capability:

Simple Reflex Agents14

Model-Based Reflex Agents
Goal-Based Agents
Utility-Based Agents

Simple reflex agents:

Simple reflex agents ignore the rest of the percept history and act only on the basis
 of the current percept.
The agent function is based on the condition-action rule.
If the condition is true, then the action is taken, else not. This agent function only
succeeds when the environment is fully observable.

Model-based reflex agents:

The Model-based agent can work in a partially observable environment, and track the
situation.
A model-based agent has two important factors:
Model: It is knowledge about "how things happen in the world," so it is called a Model-
based agent.
Internal State: It is a representation of the current state based on percept history.

Goal-based agents:
A goal-based agent has an agenda.
It operates based on a goal in front of it and makes decisions based on how best to
reach that goal.
A goal-based agent operates as a search and planning function, meaning it targets the
goal ahead
and finds the right action in order to reach it.
Expansion of model-based agent.

Utility-based agents:
A utility-based agent is an agent that acts based not only on what the goal is, but the
best way to reach
that goal.
The Utility-based agent is useful when there are multiple possible alternatives, and an
agent has
to choose in order to perform the best action.
The term utility can be used to describe how "happy" the agent is.
Environment-Types:
1. Accessible vs. inaccessible or fully observable vs Partially Observable:
If an agent sensor can sense or access the complete state of an environment at each point
of
time then it is a fully observable environment, else it is partially observable.

2. Deterministic vs. Stochastic:

If the next state of the environment is completely determined by the current state and the
actions selected by the agents, then we say the environment is deterministic

3. Episodic vs. no episodic:

The agent's experience is divided into "episodes." Each episode consists of the agent
perceiving and then acting. The quality of its action depends just on the episode itself,
because subsequent episodes do not depend on what actions occur in previous episodes.
Episodic environments are much simpler because the agent does not need to think
ahead.

4. Static vs. dynamic.

If the environment can change while an agent is deliberating, then we say the environment
isodynamic for that agent; otherwise, it is static.12

5. Discrete vs. continuous:

If there are a limited number of distinct, clearly defined precepts and actions we
say that the environment is discrete. Otherwise, it is continuous.