Fundamentals of Artificial Intelligence

3170319
Unit – 1
Prof. Bhavin Mehta
Biomedical Dept., LDCE
Syllabus Content
Course Outcomes:
List of Experiments
Unit – 1 Introduction to AI
 Introduction
 The Turing Test
 Roots of AI
 Techniques Used in AI
 Subfields of AI
 Considerations for Knowledge Representation
Learning Outcomes of Unit - 1

 Defining AI
 Describe Turing test thought experiment
 Differentiate between the concepts of optimal reasoning/behavior and
humanlike reasoning/behavior.
 Sub-fields of AI.
 Determine the characteristics of a given problem that an intelligent system
(i.e., AI-based system) must solve.
What is AI?
 Artificial Intelligence(AI) is everywhere around us,
 voice recognition software in your mobile phone or navigations in car.
 Netflix, amazon prime movie suggestions
 Interacting with Siri, Alexa, Google Assistant

 Artificial Intelligence is a broad area of Computer Science, it makes machines seem

like they have human Intelligence.
 Artificial Intelligence is not just about Programming a computer to obey rules to
drive a car.
 But an Artificial Intelligence should function much more effectively and be
independent like a human to a certain extent to make decisions.
 “Artificial Intelligence can be defined as a branch of computer science
concerned with studying and creating computer systems that can exhibit or
replicate human intelligence.”
Types of AI
Cont.…
What AI requires :
 AI requires an understanding of related terms such as intelligence, knowledge, reasoning,
thoughts, learning, and a number of computer-related terms. Data is an important aspect of AI.
Goals of AI :
• To create machines that can do better performance than the previous version.
• To add new features that humans possess.

Application Areas of AI:

• Banking to organize operations, invest in stocks, and manage properties.
• Augmented reality, Robotics
• Image and speech recognition
• Fraud detection
• Emotional recognition
• Security/Authentication
Intelligence
 A compact definition of Intelligence is:

Intelligence = Perceive + Analyze + React

“Intelligence is a very general mental capability that, among other things, involves the ability to
reason, plan, solve problems, think abstractly, comprehend complex ideas, learn quickly, and
learn from experience.”

The foundation materials of AI comprises

• Data structures
• Knowledge representation techniques
• Algorithms to apply the knowledge and language,
• Programming techniques to implement all
About AI
 Layman - “Artificial Intelligence is a terminator like figure that can act and think on its own”
 AI researcher - it’s a set of algorithms that can produce results without having to be
explicitly instructed to do so.

 “The intelligence demonstrated by machines is known as Artificial Intelligence”.

 It is the simulation of natural intelligence in machines that are programmed to learn and

mimic the actions of humans. These machines are able to learn with experience and perform
human-like tasks.
A Brief History of Artificial Intelligence

 Here’s a brief timeline of the past six decades of how AI evolved from its inception.

 1956 - John McCarthy coined the term ‘artificial intelligence’ and had the first AI conference.

 1969 - Shakey was the first general-purpose mobile robot built. It is now able to do things with a purpose vs. just a list

of instructions.

 1997 - Supercomputer ‘Deep Blue’ was designed, and it defeated the world champion chess player in a match. It was

a massive milestone by IBM to create this large computer.

 2002 - The first commercially successful robotic vacuum cleaner was created.

 2005 - 2019 - Today, we have speech recognition, robotic process automation (RPA), a dancing robot, smart

homes, and other innovations make their debut.

 2020 - Baidu releases the LinearFold AI algorithm to medical and scientific and medical teams developing a vaccine

during the early stages of the SARS-CoV-2 (COVID-19) pandemic. The algorithm can predict the RNA sequence of

the virus in only 27 seconds, which is 120 times faster than other methods.
How do we measure if Artificial Intelligence is acting like a human?

 Even if we reach that state where an AI can behave as a human does, how can we be sure it can continue

to behave that way?

 Turing Test

 The Cognitive Modelling Approach

 The Law of Thought Approach

 The Rational Agent Approach

The Turing Test
 In 1950, Alan M. Turing proposed an empirical test for machine intelligence, now called Turing Test

 “It is designed to measure the performance of an intelligent machine against humans, for its

intelligent behavior.”

 Turing called it imitation game, where machine and human counter-part are put in different rooms, separate

from a third person, called interrogator.

 The interrogator is not able to see or speak directly to any of the other two, and does not know which entity

is a machine, and communicates to these two solely by textual devices like a dumb terminal.
The Turing Test

 The interrogator is supposed to distinguish the machine from the human solely based on the answers

received for the questions asked over the interface device, which is a keyboard (or teletype).

 Even after having asked the number of questions, if the interrogator is not able to distinguish the

machine from the human, then as per the argument of Alan Turing, the machine can be considered
intelligent.

 Interrogator may ask highly computation oriented questions to identify the machine, and other questions

related to general awareness, poetry, etc., to identify the human

The Turing Test
 Many researchers argue that the Turing test is not sufficient to establish the presence of
intelligence.
Some of the arguments for and against the above test can be as follows:
 It takes human being as a reference for intelligent behavior, rather than debating over the true
nature of intelligence: against. %
 The unmeasurable things are not considered, e.g., whether a computer uses internal structures, or
for example, whether the machine is conscious of its actions, which are currently not answerable:
against.
 Eliminates any bias to human oriented interaction mechanisms, since a computer terminal is used
as a communication device: for.
 Biased towards only symbolic problem solving: against.
 Perceptual skills or dexterity cannot be checked: against.
 Unnecessarily constrains the machine intelligence to human intelligence: against.
 Though, the number of counts of against are far more than for, there is yet no known test which is
considered better than the Turing Test.
Cognitive Modelling Approach

 Approach tries to build an Artificial Intelligence model based on

Human Cognition.
 To distil the essence of the human mind, there are 3 approaches:
• Introspection: observing our thoughts, and building a model based on that
• Psychological Experiments: conducting experiments on humans and
observing their behavior
• Brain Imaging: Using MRI to observe how the brain functions in different
scenarios and replicating that through code.
The Laws of Thought Approach

 The Laws of Thought are a large list of logical statements that govern the
operation of our mind.
 The same laws can be codified and applied to artificial intelligence
algorithms.
 The issue with this approach, is because solving a problem in principle
(strictly according to the laws of thought) and solving them in practice can
be quite different.
The Rational Agent Approach

 A rational agent acts to achieve the best possible outcome in its present
circumstances.

 According to the Laws of Thought approach, an entity must behave

according to the logical statements. But there are some instances, where
there is no logical right thing to do, with multiple outcomes involving different
outcomes and corresponding compromises.
 The rational agent approach tries to make the best possible choice in the
current circumstances. It means that it’s a much more dynamic and
adaptable agent.
Techniques Used in AI
 The AI systems have a lot of variations, for example, the rule-based systems are
based on symbolic representations, and work on inferences.
 There are other extremes, the ANN-based system work on the interface with other
neurons, and connection weights.
1. Representation
 All AI systems have an important feature of knowledge representation.
 The rule-based systems, frame-based systems, and semantic networks make use of
a sequence of if-then rules, while the artificial neural networks make use of
connections along with connection weights.
2. Learning
 All AI systems have the capability of learning, using which they automatically
build-up the knowledge from the environment,
 e.g., acquiring the rules for a rule-based expert system, or determining the
appropriate connection weights in an artificial neural network.
Techniques Used in AI

3. Rules
 The rules of an AI-based system can be implicit or explicit.
 When explicit, the rules are created by a knowledge engineer, say, for an expert
system, and when implicit, they can be, for example, in the form of connection
weights in a neural network.
4. Search
 The search can be in many forms, for example, searching the sequence of states
that lead to solution faster, or searching for an optimum set of connection weights in
an ANN by minimizing the fitness function.
Subfield of AI

 Commercial,
 Industrial,
 Medicines and drug decisions,
 medical science,
 consumer products,
 manufacturing processes,
 management
Considerations for Knowledge Representation
 The following are the aspects of knowledge representation:
 What is the meaning of Knowledge?
 How the Knowledge can be represented in the machine?
 What are the requirements of representation of knowledge, e.g., structures, methods, size, etc.
 How the practical and theoretical aspects differ for knowledge representation?
 Can it be? Or, if yes, how to represent the knowledge using Natural Language?
 Can we call the databases as a form of knowledge representation?
 What are the semantic networks, and what are the frames? How the knowledge can be
represented using these approaches?
 How the knowledge can be represented using the First-Order Predicate Logic (FOPL)?
 What is a Rule-Based Systems?
 What is an expert system?
 Out of the many techniques, which is the best technique for knowledge representation?
Defining the Knowledge

 As per the Webster English language dictionary, the following are the meanings of
knowledge:
 The act or state of knowing; clear perception of fact, truth, or duty; certain
apprehension; familiar cognizance; cognition. [1913 Webster] Knowledge, which is the
highest degree of the speculative faculties, consists in the perception of the truth
of affirmative or negative propositions—Locke. [1913 Webster]
Objective of Knowledge Representation

 To express the knowledge in computer so that the AI programs can use it to perform
reasoning and inferences using this in an efficient way.
 The knowledge is represented using certain representation language for example, a predicate
like language.
 The language has two important components in it.
 Syntax
 The system of a language defines the methods using which we or the machine can distinguish
the correct structures from incorrect, i.e., it makes possible to identify the structurally valid
sentences.
 Semantics
 The semantics of a language defines the world, or facts in the world of the concerned domain.
And, hence defines the meaning of the sentence in reference, to the world.
Requirements of a Knowledge Representation

 A good knowledge representation system for any particular domain should possess the following
properties.
1. Adequacy of representation :- The representation system should be able to represent all
kind of knowledge needed in the concerned AI-based system.
2. Adequacy of Inference :- The representation should be such that all that can be inferable by
manipulating the given knowledge structures should be inferred by the system, when
needed
3. Inference Efficiency :- The knowledge structures in the representation are so organized that
the attention of the system, in the form of deductions, navigates in such a direction that
it can reach the goal quickly.
4. Efficient acquisition :- It should be able to acquire the new information automatically and
efficiently, as and when needed, and also to update the knowledge regularly. In addition,
there should be a provision that knowledge engineer can update the information in the
system.
Practical Aspects of Representations
There are many theoretical requirements for good knowledge representations, which can be met by
dealing with a number of practical aspects, as follows:
 The representations should be complete, so that everything needs to be represented, can easily
be represented.
 The representations should be simple and clear, so that one can easily understand what is being
communicated by the representation,
 The important objects and their relations should be explicit and accessible, so that it becomes
easy to see what is going on, and how the components of knowledge interact with each other.
 The irrelevant detail of the knowledge should be suppressed in the representation, so that they do
not introduce complications. However, when needed, these are still available.
 The representation should be concise, so that information can be stored, retrieved and
manipulated rapidly.
 The representation should be such that the overall system is fast.
 They must be computable and implementable with standard computing procedures.
Components of a Representation
 To carry out the analysis of any representation system, it is useful to break the entire representation
into smaller (smallest) components, which are in the most fundamental form.
 Accordingly, the components of an AI representation are divided into the four fundamental
components:

 Lexical components : - Symbols and words of the vocabulary used for representation

 Syntactic/Structural components :- how the symbols can be arranged systematically to create

meaningful sentences. These structures are the grammar of the language used for representation.

 Semantic components :- It associating real-world meaning to objects and entities.

 Procedural components :- These procedures are used for creating and modifying the representations,

and also for answering the questions using these procedures

Knowledge Representation Using Natural
Language
 We humans are intelligent beings, who make use of the knowledge represented in the form of
natural language (like, English, Hindi, Chinese, etc.), we update that knowledge (i.e.,
acquisition), and do the reasoning and inferences using this representation.
 Of course, there are many other types of knowledge representation and inferencing with the
humans, which are not symbolic-based, like those acquired through smell, touch, hearing,
and taste (through tongue).
 Hence, why not use the natural language for knowledge representation for machines also? The
following are the trade-offs for representation using natural language
 Advantages
 The natural language is strong at expressiveness, using which
we can represent almost everything (real-world situations,
pictures, symbols, ideas, emotions) and can carry out the
reasoning using that.
 It is the most abundantly used source for knowledge
representation by humans, for example, can we list the name
of textbooks not written in natural language? It is hard to reply!
 Disadvantages
 The syntax and semantics of the natural language are very complex, which are not so easily
understood. Hence, it becomes challenging and risky if solely depended on machines.
 The uniformity in representation is lacking—the sentences carrying the identical meaning can be
represented in many different syntax (structures).
 There is a lot of ambiguity in the natural language, a sentence/word may have many different
meanings, and the meanings are context-dependent.
 Hence, it is overly risky to try these for machines, unless the machines are having intelligence at
par with the human.
Roots of AI
Artificial Intelligence has identifiable roots in a number of older disciplines, particularly:
 Philosophy
 Logic/Mathematics
 Computation Psychology/Cognitive Science
 Biology/Neuroscience
 Evolution

There is inevitably much overlap, e.g. between philosophy and logic, or between mathematics
and computation.
By looking at each of these in turn, we can gain a better understanding of their role in AI, and
how these underlying disciplines have developed to play that role