UNIT 1

1.1 Artificial Intelligence

It is the science and engineering of making intelligent machines, especially intelligent computer
programs. It is related to the similar task of using computers to understand human intelligence.
Intelligence: “ability to learn, understand and think” . The branch of computer science
concerned with making computers behave like humans. The term was coined in 1956 by John
McCarthy at the Massachusetts Institute of Technology.

AI is the study of how to make computers make things which at the moment people do better.
Intelligence is the computational part of the ability to achieve goals in the world.
• Intelligence is the “the capacity to learn and solve problems”.
• in particular,
• the ability to solve novel problems
• the ability to act rationally
• the ability to act like humans
• What is AI?

Thinking Thinking
humanly rationally

Acting Acting
humanly rationally

• Examples:
• Speech recognition, Smell, Face, Object, Intuition, Inferencing, Learning new skills,
Decision making, Abstract thinking
• e.g., speech recognition and understanding and synthesis
• e.g., image understanding
• e.g., ability to take actions, have an effect
• Reasoning and Planning
• modeling the external world
• solving new problems, planning, and making decisions
• ability to deal with unexpected problems, uncertainties
•
1.2 Academic Disciplines relevant to AI
 Philosophy Logic, methods of reasoning, mind as physical system, foundations of
learning, language, rationality.
 • Mathematics Formal representation and proof, algorithms, computation,
(un)decidability, (in)tractability

• Probability/Statistics modeling uncertainty, learning from data

• Economics
• Neuroscience
• Psychology/
Computer
• Control theory
• Linguistics
utility, decision theory, rational economic agents
neurons as information processing units.
how do people behave, perceive, process cognitive
building fast computers engineering
design systems that maximize an objective
function over time .
knowledge representation, grammars.

1.3 Overview of Artificial Intelligence

• Intelligent behaviour

– Learn from experience

– Apply knowledge acquired from experience
– Handle complex situations
– Solve problems when important information is missing
– Determine what is important
– React quickly and correctly to a new situation
– Understand visual images
– Process and manipulate symbols
– Be creative and imaginative
– Use heuristics
1.4 Major Branches of AI
– Perceptive system
• A system that approximates the way a human sees, hears, and feels objects
– Vision system
• Capture, store, and manipulate visual images and pictures
– Robotics
• Mechanical and computer devices that perform tedious tasks with high
precision
– Expert system
• Stores knowledge and makes inferences
– Learning system
• Computer changes how it functions or reacts to situations based on feedback
– Natural language processing
• Computers understand and react to statements and commands made in a
“natural” language, such as English
– Neural network
 • Computer system that can act like or simulate the functioning of the human brain

1.5 Intelligent Systems in Your Everyday Life

• Post Office
– automatic address recognition and sorting of mail
• Banks
– automatic check readers, signature verification systems
– automated loan application classification
• Customer Service
– automatic voice recognition
– The Web
– Identifying your age, gender, location, from your Web surfing
– Automated fraud detection
– Digital Cameras
– Automated face detection and focusing
– Computer Games
– Intelligent characters/agents

1.6 History of AI
• 1943: early beginnings
– McCulloch & Pitts: Boolean circuit model of brain
• 1950: Turing
– Turing's "Computing Machinery and Intelligence“
• 1956: birth of AI
– Dartmouth meeting: "Artificial Intelligence“ name adopted
• 1950s: initial promise
– Early AI programs, including
– Samuel's checkers program
– Newell & Simon's Logic Theorist
– 1955-65: “great enthusiasm”
– Newell and Simon: GPS, general problem solver
– Gelertner: Geometry Theorem Prover
 – McCarthy: invention of LISP
• 1966—73: Reality dawns
– Realization that many AI problems are intractable
– Limitations of existing neural network methods identified
• Neural network research almost disappears
• 1969—85: Adding domain knowledge
– Development of knowledge-based systems
– Success of rule-based expert systems,
• E.g., DENDRAL, MYCIN
• But were brittle and did not scale well in practice
• 1986-- Rise of machine learning
– Neural networks return to popularity
– Major advances in machine learning algorithms and applications
– 1990-- Role of uncertainty
– Bayesian networks as a knowledge representation framework
– 1995-- AI as Science
– Integration of learning, reasoning, knowledge representation
– AI methods used in vision, language, data mining, etc
–
1.7 Different Types of Artificial Intelligence
1. Modeling exactly how humans actually think
2. Modeling exactly how humans actually act
3. Modeling how ideal agents “should think”
4. Modeling how ideal agents “should act”

Acting humanly: Turing test

• Turing (1950) "Computing machinery and intelligence“

• "Can machines think?"  "Can machines behave intelligently?“
• Operational test for intelligent behavior: the Imitation Game
• Suggests major components required for AI:
- knowledge representation
- reasoning,
- language/image understanding,
- learning
* Question: is it important that an intelligent system act like a human?

Thinking humanly

• Cognitive Science approach

– Try to get “inside” our minds
– E.g., conduct experiments with people to try to “reverse-engineer” how we
reason, learning, remember, predict
– Problems
– Humans don’t behave rationally
 • e.g., insurance
– The reverse engineering is very hard to do
– The brain’s hardware is very different to a computer program
Thinking rationally

• Represent facts about the world via logic

• Use logical inference as a basis for reasoning about these facts
• Can be a very useful approach to AI
– E.g., theorem-provers
– Limitations
– Does not account for an agent’s uncertainty about the world
• E.g., difficult to couple to vision or speech systems
– Has no way to represent goals, costs, etc (important aspects of real-world
environments)
Acting rationally

• Decision theory/Economics
– Set of future states of the world
– Set of possible actions an agent can take
– Utility = gain to an agent for each action/state pair
– An agent acts rationally if it selects the action that maximizes its “utility”
• Or expected utility if there is uncertainty
• Emphasis is on autonomous agents that behave rationally (make the best
predictions, take the best actions)
– on average over time
within computational limitations (“bounded rationality”)

1.8 The Agent

• An agent is anything that can be viewed as perceiving its environment through sensors
and acting upon that environment through actuators
• Human agent: eyes, ears, and other organs for sensors; hands,legs, mouth, and other
body parts for actuators
• Robotic agent: cameras and infrared range finders for sensors;various motors for
actuators.
• A human agent has :
– Sensors: eyes, ears, and other organs.
– Actuator: hands, legs, mouth, and other body part.
• A robotic agent might have:
– Sensors: Cameras,..
– Actuator: motors
• A Software Agent
– Sensors: ?
– Actuator: ?
• The agent function
maps from percepts histories to actions
F: P A
 1.8.1 Intelligent Agent
• Agent: entity in a program or environment capable of generating action.
• An agent uses perception of the environment to make decisions about actions to take.
• The perception capability is usually called a sensor.
• The actions can depend on the most recent perception or on the entire history (percept
sequence).

Environment
Environment
Sensors

Percept (Observations)

Agent Function
Agent
Actuator

Action Environment
Environment

1.9 Agent Function

• The agent function is a mathematical function that maps a sequence of perceptions into
action.
• The function is implemented as the agent program.
• The part of the agent taking an action is called an actuator.
• environment  sensors  agent function  actuators  environment

1.10 Environment
Task environment – the problem that the agent is a solution to.

• Discrete / Continuous − If there are a limited number of distinct, clearly defined, states
of the environment, the environment is discrete (For example, chess); otherwise it is
continuous (For example, driving).

• Observable / Partially Observable − If it is possible to determine the complete state of

the environment at each time point from the percepts it is observable; otherwise it is only
partially observable.
 • Static / Dynamic − If the environment does not change while an agent is acting, then it is
static; otherwise it is dynamic.

• Single agent / Multiple agents − The environment may contain other agents which may
be of the same or different kind as that of the agent.

• Accessible / Inaccessible − If the agent’s sensory apparatus can have access to the
complete state of the environment, then the environment is accessible to that agent.

• Deterministic / Non-deterministic − If the next state of the environment is completely

determined by the current state and the actions of the agent, then the environment is
deterministic; otherwise it is non-deterministic.

• Episodic / Non-episodic − In an episodic environment, each episode consists of the

agent perceiving and then acting. The quality of its action depends just on the episode
itself. Subsequent episodes do not depend on the actions in the previous episodes.
Episodic environments are much simpler because the agent does not need to think ahead.

1.11 Structure of agents

• A simple agent program can be defined mathematically as an agent function which maps
every possible percepts sequence to a possible action the agent can perform or to a
coefficient, feedback element, function or constant that affects eventual actions:
• Agent function is an abstract concept as it could incorporate various principles of
decision making like calculation of utility of individual options, deduction over logic
rules, fuzzy logic, etc.
• The program agent, instead, maps every possible percept to an action.
• We use the term percept to refer to the agent's perceptional inputs at any given instant. In
the following figures an agent is anything that can be viewed as perceiving its
environment through sensors and acting upon that environment through actuators.
1.12 Types of intelligent agents
Russell & Norvig (2003) group agents into five classes based on their degree of perceived
intelligence and capability
• simple reflex agents
• model-based reflex agents
• goal-based agents
• utility-based agents
• learning agents
1.12.1Simple reflex agents
• Simple reflex agents act only on the basis of the current percept, ignoring the rest of the
percept history. The agent function is based on the condition-action rule: if condition
then action.
• This agent function only succeeds when the environment is fully observable. Some reflex
agents can also contain information on their current state which allows them to disregard
conditions whose actuators are already triggered.
 • Infinite loops are often unavoidable for simple reflex agents operating in partially
observable environments. Note: If the agent can randomize its actions, it may be possible
to escape from infinite loops.

1.12.2 Model-based reflex agents

• A model-based agent can handle a partially observable environment. Its current state is
stored inside the agent maintaining some kind of structure which describes the part of the
world which cannot be seen. This knowledge about "how the world works" is called a
model of the world, hence the name "model-based agent".
• A model-based reflex agent should maintain some sort of internal model that depends on
the percept history and thereby reflects at least some of the unobserved aspects of the
current state. It then chooses an action in the same way as the reflex agent.

1.12.3 Goal-based agents

• Goal-based agents further expand on the capabilities of the model-based agents, by using
"goal" information. Goal information describes situations that are desirable. This allows
the agent a way to choose among multiple possibilities, selecting the one which reaches a
goal state. Search and planning are the subfields of artificial intelligence devoted to
finding action sequences that achieve the agent's goals.
 • In some instances the goal-based agent appears to be less efficient; it is more flexible
because the knowledge that supports its decisions is represented explicitly and can be
modified.

1.12.4 Utility-based agents

• Goal-based agents only distinguish between goal states and non-goal states. It is possible
to define a measure of how desirable a particular state is. This measure can be obtained
through the use of a utility function which maps a state to a measure of the utility of the
state. A more general performance measure should allow a comparison of different world
states according to exactly how happy they would make the agent. The term utility, can
be used to describe how "happy" the agent is.
• A rational utility-based agent chooses the action that maximizes the expected utility of
the action outcomes- that is, the agent expects to derive, on average, given the
probabilities and utilities of each outcome. A utility-based agent has to model and keep
track of its environment, tasks that have involved a great deal of research on perception,
representation, reasoning, and learning.
•

1.12.5 Learning agents

• Learning has an advantage that it allows the agents to initially operate in unknown
environments and to become more competent than its initial knowledge alone might
 allow. The most important distinction is between the "learning element", which is
responsible for making improvements, and the "performance element", which is
responsible for selecting external actions.
• The learning element uses feedback from the "critic" on how the agent is doing and
determines how the performance element should be modified to do better in the future.
The performance element is what we have previously considered to be the entire agent: it
takes in percepts and decides on actions.
• The last component of the learning agent is the "problem generator". It is responsible for
suggesting actions that will lead to new and informative experiences.
•

1.13 Agents and environments

• The agent function maps from percept histories to actions:
[f: P*  AAgents and environments]
The agent program runs on the physical architecture to produce f
• agent = architecture + program
Vacuum-cleaner world

• Percepts: location and contents, e.g., [A,Dirty]

• Actions: Left, Right, Suck, NoOp

1.14 Rational Agent

• A rational agent is one that can take the right decision in every situation.
 • Performance measure: a set of criteria/test bed for the success of the agent's behavior.
• The performance measures should be based on the desired effect of the agent on the
environment.

• Agent AutonomyAn agent is omniscient if it knows the actual outcome of its actions. Not
possible in practice.
• An environment can sometimes be completely known in advance.
• Exploration: sometimes an agent must perform an action to gather information (to
increase perception).
• Autonomy: the capacity to compensate for partial or incorrect prior knowledge (usually
by learning).

1.14.1 Strong AI
Strong AI is about building a machine that is capable of emulating the human mind to such
an extent that it matches or exceeds it. Strong AI requires the intelligent agent to think
outside and beyond the programming guidelines given to it. These machines should be self
aware and their overall intellectual ability needs to be indistinguishable from that of a human
being.

1.14.2 Weak AI
Weak AI deals with the creation of some form of artificial intelligence that even if reasons
and solve problems does not demonstrate mental states and consciousness as is expected
from Strong AI.Weak AI is a system that uses a set of pre-programmed rules to apply them to
any task to reach a successful completion.Simply it is a complex set of "if-then" rules of
rationality. Weak AI is not as "hi fi" as Strong AI, but Weak AI is more practical and is
being put to use rapidly.
1.15 PEAS
• PEAS: Performance measure, Environment, Actuators, Sensors
• Must first specify the setting for intelligent agent design
• Consider, e.g., the task of designing an automated taxi driver:
– Performance measure
– Environment
– Actuators
– Sensors
• Must first specify the setting for intelligent agent design

Agent : Designing an automated taxi driver:

– Performance measure: Safe, fast, legal, comfortable trip, maximize profits
– Environment: Roads, other traffic, pedestrians, customers
– Actuators: Steering wheel, accelerator, brake, signal, horn
Sensors: Cameras, sonar, speedometer, GPS, odometer, engine sensors, keyboard
Agent: Medical diagnosis system
 Performance measure: Healthy patient, minimize costs, lawsuits
• Environment: Patient, hospital, staff
• Actuators: Screen display (questions, tests, diagnoses, treatments, referrals)
• Sensors: Keyboard (entry of symptoms, findings, patient's answers)

Agent: Part-picking robot

• Performance measure: Percentage of parts in correct bins
• Environment: Conveyor belt with parts, bins
• Actuators: Jointed arm and hand
• Sensors: Camera, joint angle sensors

Agent: Interactive English tutor

• Performance measure: Maximize student's score on test
• Environment: Set of students
• Actuators: Screen display (exercises, suggestions, corrections)
• Sensors: Keyboard

1.16 Vision
Vision is the process of discovering what is present in the world and where it is by
looking.

1.17 Computer Vision

• Computer vision is concerned with modeling and replicating human vision using
computer software and hardware. It combines knowledge in computer science, electrical
engineering, mathematics, physiology, biology, and cognitive science. It needs
knowledge from all these fields in order to understand and simulate the operation of the
human vision system.
Computer Vision is the study of analysis of pictures and videos in order to achieve results
similar to those as by people.

• Computer vision (image understanding) is a discipline that studies how to reconstruct,

interpret and understand a 3D scene from its 2D images in terms of the properties of the
structures present in the scene.
Given an image or more, extract properties of the 3D world
 • Traffic scene
• Number of vehicles
• Type of vehicles
• Location of closest obstacle
• Assessment of congestion

• In the simplest terms, computer vision is the discipline of "teaching machines how to see.
• There are two major themes in the computer vision literature: 3D geometry and
recognition.
• The first theme is about using vision as a source of metric 3D information: given one or
more images of a scene taken by a camera with known or unknown parameters, how can
we go from 2D to 3D, and how much can we tell about the 3D structure of the
environment pictured in those images?
• The second theme, by contrast, is all about vision as a source of semantic information:
can we recognize the objects, people, or activities pictured in the images, and understand
the structure and relationships of different scene components just as a human would?

1.18 Computer Vision Hierarchy

•Low-level vision: process image for feature extraction (edge, corner, or optical flow).
•Intermediate-level vision: object recognition and 3D scene interpretation using features
obtained from the low-level vision.
 •High-level vision: interpretation of the evolving information provided by the intermediate
level vision as well as directing what intermediate and low level vision tasks should be
performed. Interpretation may include conceptual description of a scene like activity,
intention and behavior

1.19 Related Fields

Computer vision overlaps significantly with the following fields:
• image processing, pattern recognition, and photogrammetry.
• Image processing focuses on image manipulation to enhance image quality, to restore an
image or to compress/decompress an image. Most computer vision algorithms usually
assumes a significant amount of image processing has taken place to improve image
quality.
• Pattern recognition studies various techniques (such as statistical techniques, neural
network, support vector machine, etc..) to recognize/classify different patterns. Pattern
recognition techniques are widely used in computer vision.
• Photogrammetry is concerned with obtaining accurate and reliable measurements from
images. It focuses on accurate mensuration. Camera calibration and 3D reconstruction
are two areas of interest to both computer vision and photogrammetry researchers.
Examples
 Robotics
 Medicine
 Security
Industrial Automation

• Industrial inspection (defect detection)

• Assembly
• Barcode and package label reading
• Object sorting
• Document understanding (e.g. OCR)
Medicine
• Classification and detection (e.g. cells classification and tumor detection)
• 2D/3D segmentation
• 3D human organ reconstruction (MRI or ultrasound)
• Vision-guided robotics surgery
Security
• Biometrics (iris, finger print, face recognition)
• Surveillance-detecting certain suspicious activities or behaviours
1.20 Computer Vision vs. Machine Learning
• Machine learning is a scientific discipline that is concerned with the design and
development of algorithms that allow computers to change behavior based on data, such
as from sensor data or databases .
 A major focus of machine learning research is to automatically learn to recognize
complex patterns and make intelligent decisions based on data.
• Machine Learning is very useful for Computer Vision (e.g., learning for vision)
• Computer Vision is more than just learning
– Modeling
– Example based learning
• In Machine Learning, it usually does not care about how to obtain the data or sensors
• In Computer Vision, we care how to obtain the visual data (sensor design, active vision),
how to represent the visual data, and others
1.20 Natural language processing
Language, ability to speak , write and communicate is one of the most fundamental aspects of
human behaviour. As the study of human-languages developed the concept of communicating
with non-human devices was investigated. This is the origin of natural language processing
(NLP). The idea of natural language processing is to design and build a computer system that
will analyze , understand and generate natural human-languages.

Natural Language Processing is a technique where mechine can become more human and
there by reducing the distance between human and the mechine can be reduced.
Therefore in simple sence NLP makes human to communicate with the mechine easily.
NLP is the branch of computer science focused on developing systems that allow
computers to communicate with people using everyday language. Also called
Computational Linguistics. Also concerns how computational methods can aid the
understanding of human language

Applications
• Text-based applications
This involves applications such as searching for a certain topic or a keyword in a data
base, extracting information from a large document, translating one language to another
or summarizing text for different purposes.
 Dialogue based applications
Some of the typical examples of this are answering systems that can answer questions,
services that can be provided over a telephone without an operator, teaching systems,
voice controlled mechines (that take instructions by speech) and general problem solving
systems.

NLP Terminology
• Phonology − It is study of organizing sound systematically.
• Morphology − It is a study of construction of words from primitive meaningful units.
• Morpheme − It is primitive unit of meaning in a language.
• Syntax − It refers to arranging words to make a sentence. It also involves determining the
structural role of words in the sentence and in phrases.
• Semantics − It is concerned with the meaning of words and how to combine words into
meaningful phrases and sentences.
• Pragmatics − It deals with using and understanding sentences in different situations and
how the interpretation of the sentence is affected.
 • Discourse − It deals with how the immediately preceding sentence can affect the
interpretation of the next sentence.
• World Knowledge − It includes the general knowledge about the world.

Steps in NLP

There are general five steps −

• Lexical Analysis − It involves identifying and analyzing the structure of words. Lexicon
of a language means the collection of words and phrases in a language. Lexical analysis
is dividing the whole chunk of txt into paragraphs, sentences, and words.
• Syntactic Analysis (Parsing) − It involves analysis of words in the sentence for
grammar and arranging words in a manner that shows the relationship among the words.
The sentence such as “The school goes to boy” is rejected by English syntactic analyzer.
• Semantic Analysis − It draws the exact meaning or the dictionary meaning from the text.
The text is checked for meaningfulness. It is done by mapping syntactic structures and
objects in the task domain. The semantic analyzer disregards sentence such as “hot ice-
cream”.
• Discourse Integration − The meaning of any sentence depends upon the meaning of the
sentence just before it. In addition, it also brings about the meaning of immediately
succeeding sentence.
• Pragmatic Analysis − During this, what was said is re-interpreted on what it actually
meant. It involves deriving those aspects of language which require real world
knowledge.