MODULE 1

OVERVIEW OF AI

WHAT IS AI?
Artificial Intelligence refers to the phenomenon where a machine acts as a blueprint of the human mind,
by being able to understand, analyze, and learn from data through specially designed algorithms.
Artificially intelligent machines can remember human behavior patterns and adapt according to their
preferences. The major concepts closely related to AI are machine learning, deep learning and natural
language processing (NLP).
Machine Learning (ML) involves teaching machines about important concepts via examples by means of
big data that needs to be structured (in machine language) for the machines to understand. This is all
done by feeding them the right algorithms. Deep Learning is a step ahead of ML, meaning it learns
through representation but the data does not need to be structured for it to make sense of it. This is due
to the artificial neural networks that are inspired by the human neural structure.
Natural Language Processing (NLP) is a linguistic tool in computer science. It enables machines to read
and interpret human language. NLP allows an automatic translation of human language data and
enables two entities (computers and humans) who speak different languages to interact.
Applications / Examples of Artificial Intelligence.
1. Google Maps and Ride-Hailing Applications
One doesn’t have to put much thought into traveling to a new destination anymore. Instead of having
to rely on confusing address directions, you can now simply open up the handy map application on your
phone and type in your destination. So how does the application know the exact directions, the optimal
route, and even road barriers and traffic congestions? Not too long ago, only GPS (satellite-based
navigation) was used as guidance for commuting. But now, artificial intelligence is being incorporated to
give users a much more enhanced experience in regards to their specific surroundings. Via machine
learning, the app algorithm remembers the edges of the buildings that have been fed into the system
after the staff has manually identified them. This allows the addition of clear visuals of buildings on the
map. Another feature is the quality of recognizing and understanding handwritten house numbers which
help commuters reach the exact house they were looking for. Places that lack formal street signs can
also be identified with their outlines or handwritten labels. The application has been taught to
understand and identify traffic. Thus, it recommends the best route that avoids roadblocks and
congestion. The AI-based algorithm also tells users the exact distance and time they will reach their
destination as it has been taught to calculate this based on traffic conditions. Users can also view the
pictures of their locations before getting there. So by employing a similar AI technology, various ride-
hailing applications have also come into existence.

2. Face Detection and Recognition

Using virtual filters on our face when taking pictures and using face ID for unlocking our phones are two
applications of AI that are now part of our daily lives. The former incorporates face detection meaning
any human face is identified. The latter uses face recognition through which a specific face is recognised.
How does this work? Intelligent machines often match – and sometimes go even above and beyond! –
human capabilities. Human babies start recognizing facial features like eyes, nose, lips and face shapes.
But that is not all there is to a face. There are a plethora of factors that make human faces unique. Smart
machines are taught to identify facial coordinates (x, y, w, and h; that make a square around the face as
an area of interest), landmarks (eyes, nose etc), and alignment (geometric structures). This takes the
human ability to recognize faces several notches up. Face recognition is also used for surveillance and
 security by government facilities or at airports. For example, Gatwick Airport, London, uses face
recognition cameras as ID checks before allowing passengers to board the plane.

3. Text Editors or Autocorrect.

When you’re typing out documents, there are inbuilt or downloadable auto-correcting tools for editors
that check for spelling mistakes, grammar, readability, and plagiarism depending on their complexity
level. It must have taken you a while to learn your language before you became fluent in it. Similarly,
artificially intelligent algorithms also use machine learning, deep learning, and natural language
processing to identify incorrect usage of language and suggest corrections. Linguists and computer
scientists work together to teach machines grammar, just like you were taught at school. Machines are
fed with copious amounts of high-quality language data, organized in such a manner that machines can
understand it. So when you use even a single comma incorrectly, the editor will mark it red and prompt
suggestions. The next time you have a language editor check your document, know that you are using
one of the many examples of artificial intelligence.

4. Search and Recommendation Algorithms

When you want to watch your favorite movies or listen to songs or perhaps shop online, have you
noticed that the items suggested to you are perfectly aligned with your interests? This is the beauty of
AI. These smart recommendation systems learn your behavior and interests from your online activities
and offer you similar content. The personalized experience is made possible by continuous training. The
data is collected at the frontend (from the user), stored as big data and analyzed through machine
learning and deep learning. It is then able to predict your preferences by recommendations that keep
you entertained without having to search any further. Similarly, the optimized search engine experience
is another example of artificial intelligence. Usually, our top search results have the answer we’re
looking for. How does that happen? Quality controlling algorithms are fed with data to recognize high-
quality content over SEO spammed, poor content. This helps make an ascending order of search results
based on quality for the best user experience. As search engines are made up of codes, natural language
processing technology helps these applications to understand humans. In fact, they are also able to
predict what a human wants to ask by compiling top-ranked searches and predicting their queries when
they start to type. New features such as voice search and image search are also constantly being
programmed into machines. If you want to find a song that is playing at a mall, you can simply hold your
phone up to it, and a music-identifying app will tell you what it is within seconds. After sifting through
the rich database of songs, the machine will also tell you all the details related to that song.

5. Chatbots
As a customer, getting queries answered can be time-consuming. An artificially intelligent solution to
this is the use of algorithms to train machines to cater to customers via chatbots. This enables machines
to answer FAQs, and take and track orders. Chatbots are taught to impersonate the conversational
styles of customer representatives through natural language processing (NLP). Advanced chatbots no
longer require specific formats of inputs (e.g. yes/no questions). They can answer complex questions
requiring detailed responses. They will give the impression of a customer representative when, in fact,
they are just another example of artificial intelligence. 6. Digital Assistants When we have our hands full,
we often resort to ordering digital assistants to perform tasks on our behalf. When you are driving with
a cup of coffee in one hand, you might ask the assistant to call your mom. The assistant, for example, Siri
will access your contacts, identify the word “Mom”, and call the number. Interestingly, Siri is old news,
as it is an example of a lower-tier model that can only respond when spoken to and not give complex
answers. The latest digital assistants are well-versed in human language and incorporate advanced NLP
 and ML. They understand complex command inputs and give satisfactory outputs. They have adaptive
capabilities that can analyze your preferences, schedules, and habits. This allows them to systemize,
organize and plan things for you in the form of reminders, prompts and schedules.

THE IMPORTANCE OF AI
Artificial intelligence could be used to do lots of impressive tasks and jobs. AI can help designers and
artists make quick tweaks to visuals. AI can also help researchers identify “fake” images or connect
touch and sense. AI is being used to program websites and apps by combining symbolic reasoning and
deep learning. Basically, artificial intelligence goes beyond deep learning. Here are five reasons why AI is
important.
6. Artificial Intelligence will create new jobs.
It is no news that AI will replace “repetitive jobs.” It literally means that these kinds of jobs will be
automated, like what robots are currently doing in factories. Robots are rendering the humans that are
supposed to do those tasks practically jobless. And it goes further than that – many “white collar” tasks
in the fields of law, hospitality, marketing, healthcare, accounting, and others are adversely affected.
The situation seems scary because scientists are just scratching the surface as extensive research and
development of AI. AI is advancing rapidly (and it is more accessible to everybody). The great news
about AI is that it can create new jobs. Some believe that AI can create even more new jobs than ever
before. According to this school of thought, AI will be the most significant job engine the world has ever
seen. Artificial intelligence will eliminate low-skilled jobs and effectively create massive high-skilled job
opportunities that will span all sectors of the economy. For example, if AI becomes fully adapt to
language translation, it will create a considerable demand for high-skilled human translators. If the costs
of essential translations drop to nearly zero, this will encourage MORE companies that need this
particular service to expand their business operations abroad. To those who speak different languages
than the community in which they reside, this help will inevitably create more work for high-skilled
translators, boost more economic activities. As a result of this, and more people will be employed in
these companies due to the increased workload. Boosting international trade it one of the most
significant benefits of our “global” times. So yes, AI will eliminate some jobs, but it will create many,
many more.
7. Artificial Intelligence will improved healthcare.
AI can be used extensively in the healthcare industry. It is applicable in automated operations,
predictive diagnostics, preventive interventions, precision surgery, and a host of other clinical
operations. Some individuals predict that AI will completely reshape the healthcare landscape for the
better. AI is revolutionizing how the health sector works by reducing spending and improve patient
outcomes.
And here are some of the applications of artificial intelligence in healthcare:
• Doing repetitive jobs.
• Managing medical records and other data.
• Digital consultation.
• Treatment design.
• Medical management.
• Virtual nurses.
• Precision medicine.
 • Drug creation, and a myriad of other uses of AI.
8. Artificial Intelligence will revolutionize agriculture.
AI is also used in the agriculture industry extensively. Robots can be used to plant seeds, fertilized
crops and administer pesticides, among a lot of other uses. Farmers can use a drone to monitor
the cultivation of crops and also collect data for analysis.
The value-add data will be used to increase the final output. How? The data collected is analyzed
by AI on such variables as crop health and soil conditions, boosting final production, and it can
also be used in harvesting, especially for crops that are difficult to gather.
9. Artificial Intelligence will eliminate the need for you to perform tedious tasks
AI is changing the workplace, and there are plenty of reasons to be optimistic. It is used to do
lots of tedious and lengthy tasks, especially the low-skilled types of jobs that are labor-intensive.
It means that employees will be retasked away from boring jobs and bring significant and
positive change in the workplace.
For instance, artificial intelligence is used in the automotive industry to do repetitive tasks such
as performing a routine operation in the assembly line, for example. Allowing a robot to care
for well, robotic-tasks, has created a shift in the workforce.

10. AI is used to increase auto safety and decrease traffic complications.

Auto accidents are one of the most popular types of accidents that happen in America. It kills
thousands of people annually. A whopping 95 percent of these accidents are caused by human
error, meaning accidents are avoidable.
The number of accident cases will reduce as artificial intelligence is being introduced into the
industry by the use of self-driving cars. On-going research in the auto industry is looking at ways
AI can be used to improve traffic conditions.
Smart systems are currently in place in many cities that are used to analyze traffic lights at the
intersections. Avoiding congestion leads to safer movements of vehicles, bicycles, and
pedestrians.

Conclusion
Artificial intelligence is very useful in all industries as more research is being done to advance
it. The advancements in this AI tech will be most useful if it is understood and trusted. An
important part of it is that artificial intelligence and related technologies such as drones, robots,
and autonomous vehicles can create around tens of millions of jobs over the next decade.

KNOWLEDGE
Knowledge is the body of facts and principles. Knowledge can be language, concepts,
procedures, rules, ideas, abstractions, places, customs and so on. Study of knowledge is called
Epistemology.
What is knowledge representation?
Humans are best at understanding, reasoning, and interpreting knowledge. Human knows
things, which is knowledge and as per their knowledge they perform various actions in the real
world. But how machines do all these things comes under knowledge representation and
reasoning.

Knowledge representation is a study of ways of how knowledge is actually picturized and how
effectively it resembles the representation in human brain.
 Hence we can describe Knowledge representation as following:

o Knowledge representation and reasoning (KR, KRR) is the part of Artificial intelligence which
concerned with AI agents thinking and how thinking contributes to intelligent behavior of
agents.
o It is responsible for representing information about the real world so that a computer can
understand and can utilize this knowledge to solve the complex real world problems such as
diagnosis a medical condition or communicating with humans in natural language.
o It is also a way which describes how we can represent knowledge in artificial intelligence.
Knowledge representation is not just storing data into some database, but it also enables an
intelligent machine to learn from that knowledge and experiences so that it can behave
intelligently like a human.

A knowledge representation system should provide way of representing complex

knowledge and should posses the following characteristics.
• The representation should have a set of well defined syntax and semantics.
• The knowledge representation scheme should have a good expressive capacity.
• The representation must be efficient. That is, it should use only limited resources without
compromising on the expressive power.

What to Represent:
Following are the kind of knowledge which needs to be represented in AI systems:
o Object: All the facts about objects in our world domain. E.g., Guitars contains strings, trumpets are brass
instruments.
o Events: Events are the actions which occur in our world.
o Performance: It describe behavior which involves knowledge about how to do things.
o Meta-knowledge: It is knowledge about what we know.
o Facts: Facts are the truths about the real world and what we represent.
o Knowledge-Base: A knowledge base is an organized collection of facts about the system's domain. An
inference engine interprets and evaluates the facts in the knowledge base in order to provide an answer.
A knowledge-based system (KBS) is a form of artificial intelligence (AI) that aims to capture the
knowledge of human experts to support decision-making. Examples of knowledge-based systems include
expert systems, which are so called because of their reliance on human expertise.

Knowledge: Knowledge is awareness or familiarity gained by experiences of facts, data, and situations.
Following are the types of knowledge in artificial intelligence:
 Types of knowledge

Following are the various types of knowledge:

1. Declarative Knowledge:
o Declarative knowledge is to know about something and it is a passive knowledge..
o It includes concepts, facts, and objects.
o It is also called descriptive knowledge and expressed in declarative sentences.
o It is simpler than procedural language.
o Example mark statement of a student.
2. Procedural Knowledge
o It is also known as imperative knowledge.
o Procedural knowledge is a type of knowledge which is responsible for knowing how to do
something.
o It can be directly applied to any task.
o It includes rules, strategies, procedures, agendas, etc.
o Procedural knowledge depends on the task on which it can be applied.
3. Meta-knowledge:
o Knowledge about the other types of knowledge is called Meta-knowledge.
4. Heuristic knowledge:
o Heuristic knowledge is representing knowledge of some experts in a field or subject.
o Heuristic knowledge is based on previous experiences, awareness of approaches, and which are good
to work but not guaranteed.
o Heuristic knowledge are rules or tricks used to make judgement and also to simplify solutions of
problems. It is acquired through experience. An expert uses his knowledge that has gathered due to
his experience and learning.
5. Structural knowledge:
o Structural knowledge is basic knowledge to problem-solving.
o It describes relationships between various concepts such as kind of, part of, and grouping of
something.
o It describes the relationship that exists between concepts or objects.
 KNOWLEDGE-BASED SYSTEMS (KBS)

A knowledge-based system (KBS) is a form of artificial intelligence (AI) that aims to capture the knowledge
of human experts to support decision-making. Examples of knowledge-based systems include expert
systems, which are so called because of their reliance on human expertise.

The typical architecture of a knowledge-based system, which informs its problem-solving method,
includes a knowledge base and an inference engine. The knowledge base contains a collection of
information in a given field -- medical diagnosis, for example. The inference engine deduces insights from
the information housed in the knowledge base. Knowledge-based systems also include an interface
through which users query the system and interact with it.

A knowledge-based system may vary with respect to its problem-solving method or approach. Some
systems encode expert knowledge as rules and are therefore referred to as rule-based systems. Another
approach, case-based reasoning, substitutes cases for rules. Cases are essentially solutions to existing

problems that a case-based system will attempt to apply to a new problem.

KNOWLEDGE REPRESENTATION

There are mainly four ways of knowledge representation which are given as follows:
1. Logical Representation
2. Semantic Network Representation
3. Frame Representation
4. Production Rules / Scripts
1. Logical Representation

Logical representation is a language with some concrete rules which deals with propositions and has no
ambiguity in representation. Logical representation means drawing a conclusion based on various
conditions. This representation lays down some important communication rules. It consists of precisely
defined syntax and semantics which supports the sound inference. Each sentence can be translated into
logics using syntax and semantics.

Syntax:

o Syntaxes are the rules which decide how we can construct legal sentences in the logic.
o It determines which symbol we can use in knowledge representation.
o How to write those symbols.

Semantics:

o Semantics are the rules by which we can interpret the sentence in the logic.
o Semantic also involves assigning a meaning to each sentence.

Logical representation can be categorised into mainly two logics:

a. Propositional Logics
b. Predicate logics
Note: We will discuss Prepositional Logics and Predicate logics in later chapters.

Advantages of logical representation:

1. Logical representation enables us to do logical reasoning.

2. Logical representation is the basis for the programming languages.

Disadvantages of logical Representation:

1. Logical representations have some restrictions and are challenging to work with.
2. Logical representation technique may not be very natural, and inference may not be so efficient.
Note: Do not be confused with logical representation and logical reasoning as logical representation
is a
representation language and reasoning is a process of thinking logically.
2. Semantic Network Representation

Semantic networks are alternative of predicate logic for knowledge representation. In Semantic networks,
we can represent our knowledge in the form of graphical networks. This network consists of nodes
representing objects and arcs which describe the relationship between those objects. Semantic networks
can categorize the object in different forms and can also link those objects. Semantic networks are easy
to understand and can be easily extended.
This representation consist of mainly two types of relations:
a. IS-A relation (Inheritance)
b. Kind-of-relation
Example: Following are some statements which we need to represent in the form of nodes and arcs.
Statements:
a. Jerry is a cat.
b. Jerry is a mammal
c. Jerry is owned by Priya.
d. Jerry is white colored.
e. All Mammals are animal.
 In the above diagram, we have represented the different type of knowledge in the form of nodes and arcs.
Each object is connected with another object by some relation.

Drawbacks in Semantic representation:

1. Semantic networks take more computational time at runtime as we need to traverse the complete network
tree to answer some questions. It might be possible in the worst case scenario that after traversing the
entire tree, we find that the solution does not exist in this network.
2. Semantic networks try to model human-like memory (Which has 1015 neurons and links) to store the
information, but in practice, it is not possible to build such a vast semantic network.
3. These types of representations are inadequate as they do not have any equivalent quantifier, e.g., for all,
for some, none, etc.
4. Semantic networks do not have any standard definition for the link names.
5. These networks are not intelligent and depend on the creator of the system.

Advantages of Semantic network:

1. Semantic networks are a natural representation of knowledge.

2. Semantic networks convey meaning in a transparent manner.
3. These networks are simple and easily understandable.

3.Frame Representation

A frame is a record like structure which consists of a collection of attributes and its values to describe an
entity in the world. Frames are the AI data structure which divides knowledge into substructures by
representing stereotypes situations. It consists of a collection of slots and slot values. These slots may be
of any type and sizes. Slots have names and values which are called facets.

Slots Filters

Title Artificial Intelligence

Genre Computer Science

Author Peter Norvig

Edition Third Edition

Year 1996

Page 1152

Facets: The various aspects of a slot is known as Facets. Facets are features of frames which enable us to
put constraints on the frames. Example: IF-NEEDED facts are called when data of any particular slot is
needed. A frame may consist of any number of slots,
 and a slot may include any number of facets and facets may have any number of values. A
frame is also known as slot-filter knowledge representation in artificial intelligence.

Frames are derived from semantic networks and later evolved into our modern-day classes
and objects. A single frame is not much useful. Frames system consist of a collection of
frames which are connected. In the frame, knowledge about an object or event can be
stored together in the knowledge base. The frame is a type of technology which is widely
used in various applications including Natural language processing and machine visions.

Example: 1

Let's take an example of a frame for a book

Example 2:

Let's suppose we are taking an entity, Peter. Peter is an engineer as a profession, and his age
is 25, he lives in city London, and the country is England. So following is the frame
representation for this:

Slots Filter

Name Peter

Profession Doctor

Age 25

Marital status Single

Weight 78

Advantages of frame representation:

1. The frame knowledge representation makes the programming easier by grouping the
related data.
2. The frame representation is comparably flexible and used by many applications in AI.
3. It is very easy to add slots for new attribute and relations.
4. It is easy to include default data and to search for missing values.
5. Frame representation is easy to understand and visualize.

Disadvantages of frame representation:

1. In frame system inference mechanism is not be easily processed.

2. Inference mechanism cannot be smoothly proceeded by frame representation.
3. Frame representation has a much generalized approach.

4.Production Rules (or) Scripts

Production rules system consist of (condition, action) pairs which mean, "If condition
then action". It has mainly three parts:

o The set of production rules

o Working Memory
o The recognize-act-cycle

In production rules agent checks for the condition and if the condition exists then
production rule fires and corresponding action is carried out. The condition part of the rule
determines which rule may be applied to a problem. And the action part carries out the
associated problem-solving steps. This complete process is called a recognize-act cycle.
The working memory contains the description of the current state of problems- solving and
rule can write knowledge to the working memory. This knowledge match and may fire other
rules.
If there is a new situation (state) generates, then multiple production rules will be fired
together, this is called conflict set. In this situation, the agent needs to select a rule from these
sets, and it is called a conflict resolution.

Example:
o IF (at bus stop AND bus arrives) THEN action (get into the bus)
o IF (on the bus AND paid AND empty seat) THEN action (sit down).
o IF (on bus AND unpaid) THEN action (pay charges).
o IF (bus arrives at destination) THEN action (get down from the bus).

Advantages of Production rule:

1. The production rules are expressed in natural language.
2. The production rules are highly modular, so we can easily remove, add or modify an
individual rule.

Disadvantages of Production rule:

1. Production rule system does not exhibit any learning capabilities, as it does not store the
result of the problem for the future uses.
2. During the execution of the program, many rules may be active hence rule- based production
systems are inefficient.
The Knowledge Organization System (KOS)

The Knowledge Organization System (KOS) provides a framework for the different classification
schemes used to organize knowledge. Some KOSs are library classifications, taxonomies,
subject headings, thesauri, ontologies, etc. KOS is a corner stone of Knowledge Organization
tools.
Knowledge Organization techniques are used to build KOSs. These techniques outline
principles to build, manage, and visualize KOS. Knowledge Organization Systems show a
simplified view of the concepts of a domain. The goal is provide a way to improve the
understanding and the management of a field of knowledge.

Taking account of the variety of disciplines needs to facilitate their understanding, KO Systems
are present in a wide range of fields of knowledge. There are examples of KOS in e-learning,
Artificial Intelligence, Software Engineering, and Information Science. Each of these fields
gives to KO Systems one or more different names; each KOS has its own design characteristics,
according its specific goals. In this manner, e-learning talks about mind maps and concept
maps; Artificial Intelligence addresses ontologies and semantic networks; Software
Engineering talks about UML diagrams; Information Science uses thesauri, subject headings,
library classifications, etc. Although, each approach has a different semantic structure,
depending on its goals, all of them develop and maintain a domain vocabulary to represent
concepts, and semantic relationships between these concepts.

The construction of a KOS requires a high level of intellectual effort to reach an agreement
about the representation. This involves analyzing the domains to extract the main concepts
and relationships and to agree these analyses, in order to develop a shared representation.
The process can be simplified by using a suitable methodology and software applications that
have been developed to facilitate this work. Examples can be found in Software Engineering
and Ontology Engineering.

One of the main bottlenecks is knowledge acquisition. This phase tries to identify the main
concepts, by looking at different information sources and seeking the advice of domain
experts. The next step is conceptualization, by structuring the domain. This means analyzing
terminology, synonyms and hierarchical and associative structures. Also, it is important to
identify the constraints of each relation or attribute.

Knowledge Manipulation

Decisions and actions in knowledge based systems come from manipulation of the
knowledge.
The known facts in the knowledge base be located, compared, and altered in some way.
This process may set up other subgoals and require further inputs, and so on until a final
solution is found.
The manipulations are the computational equivalent of reasoning. This requires a form of
inference or deduction, using the knowledge and inferring rules.
All forms of reasoning requires a certain amount of searching and matching.
The searching and matching operations consume greatest amount of computation time in AI
systems.
It is important to have techniques that limit the amount of search and matching required to
complete any given task.

Knowledge acquisition

Knowledge acquisition is a method of learning, first proposed by Aristotle. Aristotle proposed

that the mind at birth is a blank slate, or tabula rasa. As a blank slate it contains no knowledge
of the objective, empirical universe, nor of itself. Knowledge acquisition is the process of
extracting, structuring and organizing knowledge from one source, usually human experts, so
it can be used in software such as an Expert System. This is often the major obstacle in building
an Expert System. As a method, it is opposed to the concept of "a priori" knowledge (A priori
knowledge is that which is independent from experience. Examples include mathematics,
tautologies, and deduction from pure reason, A posteriori knowledge is that which depends
on empirical evidence. Examples include most fields of science and aspects of personal
knowledge.), and to "intuition" when conceived as religious revelation. It has been suggested
that the mind is "hard wired" to begin operating at birth, beginning a lifetime process of
acquisition through abstraction, induction, and conception.