Artificial Intelligence (BAD402)

MODULE-5 QUESTION BANK-SOLUTIONS

Compiled by Dr. Amjad Khan

1. Define Uncertainty and its sources in AI?

Uncertainty in Artificial Intelligence
 Artificial intelligence (AI) uncertainty is when there’s not enough information or
ambiguity in data or decision-making.
 It is a fundamental concept in AI, as real-world data is often noisy and incomplete.
 AI systems must account for uncertainty to make informed decisions.
 AI deals with uncertainty by using models and methods that assign probabilities to
different outcomes.
 Managing uncertainty is important for AI applications like self-driving cars and
medical diagnosis, where safety and accuracy are key.
 Lack of complete information or the presence of variability in data and models.
 Understanding and modeling uncertainty is crucial for making informed decisions
and improving the robustness of AI systems.
Sources of Uncertainty in AI

2. Discuss Kolmogorov’s axioms.

Kolmogorov’s axioms define basic semantics for probabilities:
1. 0 ≤ P (a) ≤ 1 for any proposition
2. P (true) = 1 and P (false) = 0
3. P (a ∨ b) = P (a) + P (b) − P(a ∧ b)
From this, a number of useful facts can be derived,
 P(￢a) = 1 − P(a)
  For variable D with domain (d1, . . . , dn),

 And so any JPD over finite variables sums to 1

 With this, we can calculate the probability of any proposition from a
JPD
3. Explain Basic Probability Notations with examples.
Probability notation is an efficient way of writing the probability of events happening
or not happening.

 Probability. P (A) - Probability that event A will occur.

 P (A|B) - conditional probability that event A occurs, given that event
B has occurred.
 P (A′) - probability of the complement of event A.
 Below are two Venn diagrams which involve two sets and show event
A and anything that is not event A.
  Union: P (A∪B) or ‘A union B’ is the chance of picking any outcome
that is satisfied by event A or event B or both.

For example, S is the set of numbers, 1−12. A1−12. A and B are subsets of S.

A=multiples of 3.

B= multiples of 4.4.

One of the numbers is picked at random. Find the probability P (A∪B).

Event A are the multiples of 3 = 3, 6,9,12

Events B are the multiples of 4 = 4, 8, 12.

The numbers 1, 2, 5,7,10 and 11 are not in event A or B.

There are 12 possible outcomes, the numbers 1 to 12.

There are a total of 6 outcomes that satisfy event A or event B.

So P (A∪B) =6/12.

Intersection:
 P (A∩B) or ‘A intersection B’ is the chance of picking any outcome
that is satisfied by event A and event B, the joint probability of the
events.
 In a Venn diagram it would be presented like this.
 For example, S is the set of numbers, 1−12. A and B are subsets of S.
 A= multiples of 3.
 B= multiples of 4.
 One of the numbers is picked at random. Find the probability P (A∩B).
 Event A are the multiples of 3 = 3, 6,9,12.
 Event B are the multiples of 4 = 4,8,12.
 The numbers 1, 2, 5,7,10 and 11 are not in event A or B.
 There are 12 possible outcomes, the numbers 1 to 12.
 There is only 1 number that satisfies event A and event B, the number 12.
 So P (A∩B) =1/12.
4. Describe Joint Probability, Conditional Probability and Baye’s Rule.
Joint Probability:
Joint probability is a concept in probability theory that measures the likelihood of two
(or more) events happening at the same time. If A and B are two events, the joint
probability of A and B is denoted as P (A\B) or P (A, B), which represents the
probability that both events A and B occur simultaneously.
Joint probability is P(AB)=P(A/B)= P ( A ) × P ( B | A ) or P(A) x P(B)
where A & B are the events.
Conditional Probability:
Conditional probability is the probability of an event occurring given that another
event has already occurred. It is denoted as P (A|B), which reads as "the probability
of A given B."
The formula for conditional probability is:
P (A|B) = P (A ∩ B)/P (B)

Therefore, P (A ∩ B) = P (B) P (A|B) if P (B) ≠ 0

 = P (A) P (B|A) if P (A) ≠ 0

Similarly, the probability of occurrence of B when A has already occurred is given

by,

P (B|A) = P (B ∩ A)/P (A)

Baye’s Rule:
Bayes’ Theorem is used to determine the conditional probability of an event. It is
used to find the probability of an event, based on prior knowledge of conditions that
might be related to that event.

Bayes theorem (also known as the Bayes Rule or Bayes Law) is used to determine
the conditional probability of event A when event B has already occurred.

The general statement of Bayes’ theorem is “The conditional probability of an

event A, given the occurrence of another event B, is equal to the product of the
event of B, given A and the probability of A divided by the probability of event
B.” i.e.

P (A|B) = P (B|A) P (A) / P (B)

Where,

 P(A) and P(B) are the probabilities of events A and B

 P(A|B) is the probability of event A when event B

happens

 P(B|A) is the probability of event B when A happens

5. Summarize the components of Expert System with a neat diagram.

Expert systems are a specialized branch of artificial intelligence designed to mimic
and replicate human expertise and knowledge in a specific domain. They play a vital
role in AI as they can capture, represent, and utilize human expertise to solve
complex problems, make decisions, and offer valuable advice. The architecture of
expert system in AI is typically consists of three main components.
Components Expert System

The architecture of expert system in AI is typically consists of three

main components:
 Knowledge Base
 Inference Engine
 User Interface
 Knowledge Base:
This component stores the domain-specific information, rules, and facts that the
expert system uses to make decisions and solve problems. The knowledge base is
created by human experts in the domain and is a critical part of the system. It
contains both declarative knowledge (facts about the domain) and procedural
knowledge (rules and heuristics for problem-solving). The knowledge base is the
repository of facts, rules, and domain-specific information.
 Inference Engine:
The inference engine is responsible for processing the information in the knowledge
base and applying it to specific situations or problems. It uses various reasoning
techniques, such as forward chaining and backward chaining, to derive conclusions
and make decisions. The inference engine evaluates the available data and rules to
provide recommendations or solutions. The inference engine is the reasoning
component of the expert system. It processes the information in the knowledge base to
solve problems and make decisions.
 User Interface:
The user interface component allows users or operators to interact with the expert
system. It can take the form of a text-based interface or a graphical user interface
(GUI). Users can input questions or problem descriptions, and the expert system uses
its knowledge base and inference engine to provide answers, solutions, or advice. It
serves as a bridge between human users and the underlying knowledge and reasoning
components. The user interface can take various forms, including text-based
interfaces, graphical interfaces, or natural language interfaces, depending on the
design of the expert system.
6. Illustrate the need of expert system and its real-world examples in
AI.
Need of Expert Systems
Below are the points that are describing the need of the ES:
1. No memory Limitations: It can store as much data as required and can memorize
it at the time of its application. But for human experts, there are some limitations
to memorize all things at every time.
2. High Efficiency: If the knowledge base is updated with the correct knowledge,
then it provides a highly efficient output, which may not be possible for a human.
3. Expertise in a domain: There are lots of human experts in each domain, and they
all have different skills, different experiences, and different skills, so it is not easy
to get a final output for the query. But if we put the knowledge gained from human
experts into the expert system, then it provides an efficient output by mixing all
the facts and knowledge
4. Not affected by emotions: These systems are not affected by human emotions
such as fatigue, anger, depression, anxiety, etc.. Hence the performance remains
constant.
5. High security: These systems provide high security to resolve any query.
6. Considers all the facts: To respond to any query, it checks and considers all the
available facts and provides the result accordingly. But it is possible that a human
expert may not consider some facts due to any reason.
7. Regular updates improve the performance: If there is an issue in the result
provided by the expert systems, we can improve the performance of the system by
updating the knowledge base.
Real-World Example of Expert System in AI
 MYCIN: MYCIN was one of the earliest expert systems, designed for medical
diagnosis, particularly in the domain of infectious diseases. It demonstrated the
potential of expert systems in mimicking the decision-making processes of human
experts in healthcare.
 Dendral: Dendral was an expert system in the domain of organic chemistry,
specifically focused on mass spectrometry. It illustrated how expert systems could
analyze complex data and provide valuable insights.
 XCON: XCON was developed by Digital Equipment Corporation to configure
computer systems. It showcased the application of expert systems in solving
configuration problems for complex products.
 Diagnosis Expert Systems: Various expert systems are used for medical
diagnosis, such as DXplain, which helps clinicians in diagnosing complex medical
cases, and CADUCEUS, which aids in the diagnosis of infectious diseases.
 Customer Support Chatbots: Modern chatbots that provide customer support
and troubleshooting assistance often incorporate expert systems to answer user
queries and resolve issues based on predefined knowledge.
7. Discuss various methods of knowledge representation in Expert
System.
Knowledge representation is a fundamental aspect of expert systems, as it determines
how domain-specific knowledge is stored and organized. There are several methods
for knowledge representation, each with its own strengths and suitability for different
domains. It's important to understand these methods:
 Rules-based Systems: In rules-based systems, knowledge is represented using if-
then rules. These rules express relationships between conditions and actions.
 1. IF-THEN rules
 Human experts usually tend to think along :
 condition ⇒ action or Situation ⇒ conclusion
 Rules "if-then" are predominant form of encoding knowledge in expert systems.
These are of the form :
If a1 , a2 , . . . . . , an
Then b1 , b2 , . . . . . , bn where
each ai is a condition or situation, and
each bi is an action or a conclusion.
 Semantic Networks: Semantic networks represent knowledge using nodes and links
to depict relationships between concepts. They are highly visual and can show
hierarchies, associations, and attributes. Semantic networks are often used in
knowledge graphs and natural language processing tasks to represent knowledge in a
structured way.
Example of Semantic Network
 The Fig. below shows a car IS-A vehicle; a vehicle HAS wheels.
 This kind of relationship establishes an inheritance in the network, with the objects
lower down in the network inheriting properties from the objects higher up.

 Frames: Frames are a knowledge representation technique that structures information

using a frame, which is a data structure containing slots for attributes and values.
Frames are particularly useful for representing complex objects and their properties.
For example, a "patient" frame might have slots for "name," "age," and "diagnosis."
An example of Frame-based representation of knowledge
 Two frames, their slots and the slots filled with data type are shown.
8. Define knowledge acquisition and describe its process.
Knowledge acquisition is the process of extracting knowledge (facts, procedures,
rules) from human experts, books, documents, sensors or computer files and
converting it into a form that can be stored and manipulated by the computer for
purposes of problem solving. It occurs throughout the entire development process.
Knowledge acquisition (KA) is a crucial stage in the development of an expert
system.

Knowledge Acquisition Process

i). Identification: Identify the problem including data, criteria for solutions to meet,
available resources, etc.
ii).Conceptualization: Determine the key concepts and relationships by characterizing
the data flow of information, the domain structure, etc.
iii). Formalization: Understand the underlying search space, uncertainty issues, etc.
iv). Implementation: Translate acquired knowledge into the program.
v). Testing: Validate and verify.
Validation and Verification
These are terms used quality of a knowledge base. The methods are collectively
known as evaluation techniques.
i). Validation: This deals with the performance of the system i.e. how well it is
making conclusions. The common method of evaluation is the TURING TEST
ii). Verification: This deals with the building of the system to the correct
specification. The following are some of the parameters used for evaluation:
a) Turing test: - used as a measure of the effectiveness of the expert system.
b) Accuracy: - how well the system reflects the reality.
c) Adaptability: - deals with the possibilities of future changes.
d) Adequacy (completeness): - how much necessary knowledge has been included.
e) Breadth and depth: - how well the domain is covered and the degree of detail.
f) Reliability: - probability that the expert system predictions turns out to be correct.
g) Sensitivity: - Impact of changes in the knowledge base and the quality of the
Outputs
9. Implement an expert system to diagnose the problem of a car that
won’t start.
10. Explain various applications of expert system.
Applications of Expert System in AI

 Medical Diagnosis: Expert systems are widely used in healthcare for diagnosing
medical conditions. They can analyze patient symptoms, medical history, and test
results to provide accurate and timely diagnoses. An example is IBM's Watson for
Oncology, which assists in cancer treatment decisions.
 Financial Advising: Expert systems in finance provide investment advice,
portfolio management, risk assessment, and financial planning. They consider
market trends, risk tolerance, and financial goals to make recommendations.
Companies like Wealth front use expert systems to offer financial planning
services.
 Troubleshooting: Expert systems aid in troubleshooting technical issues in
various industries, such as IT support and manufacturing. They guide technicians
or end-users through a series of questions to identify problems and suggest
solutions. For instance, Apple's Support app uses expert system features to
diagnose iPhone issues.
 Natural Language Processing: In natural language processing, expert systems
are used for language understanding, sentiment analysis, and chatbots. They
enable automated responses to customer inquiries, as seen in chatbots like
Amazon's Alexa and Apple's Siri.
 Industrial Process Control: In manufacturing and industrial settings, expert
systems optimize processes, monitor equipment, and predict maintenance needs.
They help reduce downtime, enhance efficiency, and improve safety. The
AspenTech platform is an example used in process industries like oil and gas.