M.Sc.

CS (Regular) –II SEMESTER

Artificial Intelligence & Expert Systems
UNIT-5
Staff Name: Dr.Sreejith Vignesh B P, M.Sc.,MBA.,MCA.,M.Phil.,B.Ed.,PG.D.LL.AL.,Ph.D.,
--------------------------------------------------------------------------------------------------------------------------------------
UNIT V: Learning-Common sense-Perception and Action-Expert System
---------------------------------------------------------------------------------------------------------------------------------------
Learning
Synopsis
1. Introduction:
2. Definition for learning
3. Why is it hard?
4. How can we learn?
5. Skill refinement
6. Knowledge acquisition
7. Taking advice
8. Problem Solving
9. Induction
10. Discovery
11. Analogy
12. Various forms of learnings
 Rote learning
 Induction learning
 Learning by taking advice
 Automated Advice Taking
 Explanation Based Learning (EBL)
 Learning in Problem Solving
 Discovery
 Theory Driven Discovery - AM (1976)
 Data Driven Discovery -- BACON (1981)

Introduction: What is learning?

 According to Herbert Simon, learning denotes changes in a system that enable a system to do the
same task more efficiently the next time.
 Arthur Samuel stated that, "Machine learning is the subfield of computer science, that gives
computers the ability to learn without being explicitly programmed ".
 In 1997, Mitchell proposed that, “A computer program is said to learn from experience 'E' with
respect to some class of tasks 'T' and performance measure 'P', if its performance at tasks in 'T', as
measured by 'P', improves with experience E ".
 The main purpose of machine learning is to study and design the algorithms that can be used to
produce the predicates from the given dataset.
 Besides these, the machine learning includes the agents percepts for acting as well as to Improve their
future performance.
 Learning is an important area in AI, perhaps more so than planning.
 Problems are hard -- harder than planning.
 Recognized Solutions are not as common as planning.
 A goal of AI is to enable computers that can be taught rather than programmed.

1
Definition for learning
 Learning is an area of AI that focuses on processes of self-improvement.
 Information processes that improve their performance or enlarge their knowledge bases are said
to learn.

2
Why is it hard?
 Intelligence implies that an organism or machine must be able to adapt to new situations.
 It must be able to learn to do new things.
 This requires knowledge acquisition, inference, updating/refinement of knowledge base, acquisition
of heuristics, applying faster searches, etc.

How can we learn?

 Many approaches have been taken to attempt to provide a machine with learning capabilities.
 This is because learning tasks cover a wide range of phenomena.
 Listed below are a few examples of how one may learn. We will look at these in detail shortly

Skill refinement
 One can learn by practicing, e.g playing the piano.

Knowledge acquisition
 One can learn by experience and by storing the experience in a knowledge base.
 One basic Example of this type is rote learning.
Taking advice
 Similar to rote learning although the knowledge that is input may need to be transformed (Or
operationalised) in order to be used effectively.

Problem Solving
 If we solve a problem one may learn from this experience.
 The next time we see a similar problem we can solve it more efficiently.
 This does not usually involve gathering new knowledge but may involve reorganization of data or
remembering how to achieve to solution
Induction
 One can learn from examples.
 Humans often classify things in the world without knowing explicit rules.
 Usually involves a teacher or trainer to aid the classification.

Discovery
 Here one learns knowledge without the aid of a teacher.

Analogy
 If a system can recognize similarities in information already stored then it may be able to transfer
some knowledge to improve to solution of the task in hand.

Various forms of learnings

 Rote learning
 Induction learning
 Learning by taking advice
 Automated Advice Taking
 Explanation Based Learning (EBL)
 Learning in Problem Solving
 Discovery
 Theory Driven Discovery - AM (1976)
 Data Driven Discovery -- BACON (1981)
1. Rote learning
 Rote learning is possible on the basis of memorization.
 This technique mainly focuses on memorization by avoiding the inner complexities.
 So, it becomes possible for the learner to recall the stored knowledge.
3
 Rote Learning is basically memorisation

Saving knowledge so it can be used again.

 Retrieval is the only problem.
 No repeated computation, inference or query is necessary.
 A simple example of rote learning is caching
 Store computed values (or large piece of data)
 Recall this information when required by computation.
 Significant time savings can be achieved.
 Many AI programs (as well as more general ones) have used caching very effectively
 For example: When a learner learns a poem or song by reciting or repeating it, without knowing the
actual meaning of the poem or song.

2. Induction learning (Learning by example).

 Induction learning is carried out on the basis of supervised learning.
 In this learning process, a general rule is induced by the system from a set of observed instance.
 However, class definitions can be constructed with the help of a classification method.

For Example:
 Consider that 'ƒ' is the target function and example is a pair (x ƒ(x)), where 'x' is input and ƒ(x)
is the output function applied to 'x'.
Given problem: Find hypothesis h such as h ≈ ƒ
 So, in the following fig-a, points (x,y) are given in plane so that y = ƒ(x), and the task is to find
a function h(x) that fits the point well.

 In fig-b, a piecewise-linear 'h' function is given, while the fig-c shows more complicated 'h' function.

 Both the functions agree with the example points, but differ with the values of 'y' assigned to other

4
 As shown in fig.(d), we have a function that apparently ignores one of the example points, but fits
others with a simple function. The true/ is unknown, so there are many choices for h, but without
further knowledge, we have no way to prefer (b), (c), or (d).

3. Learning by taking advice

 This type is the easiest and simple way of learning.
 In this type of learning, a programmer writes a program to give some instructions to perform a
Task to the computer.
 Once it is learned (i.e. programmed), the system will be able to do new things.
 Also, there can be several sources for taking advice such as humans(experts), internet etc.
 However, this type of learning has a more necessity of inference than rote learning.
 As the stored knowledge in knowledge base gets transformed into an operational form, the
Reliability of the knowledge source is always taken into consideration

4. Automated Advice Taking

The following steps summarise this method:
Request
 This can be simple question asking about general advice or more complicated by identifying
shortcomings in the knowledge base and asking for a remedy.

Interpret
 Translate the advice into an internal representation.

Operationalise
 Translated advice may still not be usable so this stage seeks to provide a representation that can be
used by the performance element.

Integrate
 When knowledge is added to the knowledge base care must be taken so that bad side effects are
avoided.
 E.g. Introduction of redundancy and contradictions.

Evaluate
 The system must assess the new knowledge for errors, contradictions etc.
 The steps can be iterated.

5. Explanation Based Learning (EBL)

 Humans appear to learn quite a lot from one example.
 Basic idea: Use results from one examples problem solving effort next time around.
 An EBL accepts 4 kinds of input:

A training example
-- what the learning sees in the world.
5
A goal concept
-- a high level description of what the program is supposed to learn.

A operational criterion
-- a description of which concepts are usable.

A domain theory
 It is a set of rules that describe relationships between objects and actions in a domain.
 From this EBL computes a generalization of the training example that is sufficient not only to
describe the goal concept but also satisfies the operational criterion.
 This has two steps:

Explanation
-- The domain theory is used to prune away all unimportant aspects of the training example with
respect to the goal concept.

Generalization

o the explanation is generalised as far possible while still describing the goal concept.

6. Learning in Problem Solving

 There are three basic methods in which a system can learn from its own experiences.
1. Learning by Parameter Adjustment
2. Learning by Macro Operators
3. Learning by Chunking

Learning by Parameter Adjustment

 Many programs rely on an evaluation procedure to summarise the state of search etc.
 Game playing programs provide many examples of this.
 However, many programs have a static evaluation function.
 In learning a slight modification of the formulation of the evaluation of the problem is required.

Learning by Macro Operators

 The basic idea here is similar to Rote Learning:

Avoid expensive recomputation

 Macro-operators can be used to group a whole series of actions into one.

For example:
 Making dinner can be described a lay the table, cook dinner, serve dinner.
 We could treat laying the table as on action even though it involves a sequence of actions.
 The STRIPS problem-solving employed macro-operators in it's learning phase.
 Consider a blocks world example in which ON(C, B) and ON (A, TABLE) are true.
 STRIPS can achieve ON(A,B) in four steps:
 UNSTACK(C,B)
 PUTDOWN(C)
 PICKUP(A)
 STACK(A,B)
 STRIPS now builds a macro-operator MACROP with preconditions ON(C,B), ON(A,TABLE),
post conditions ON (A, B), ON(C,TABLE) and the four steps as its body.
 MACROP can now be used in future operation.

6
  But it is not very general. The above can be easily generalised with variables used in place of the
blocks.

Learning by Chunking

 Chunking involves similar ideas to Macro Operators and originates from psychological ideas on
memory and problem solving.
 The computational basis is in production systems .
 SOAR is a system that use production rules to represent its knowledge. It also employs chunking to
learn from experience.

7. Discovery
 Discovery is a restricted form of learning in which one entity acquires knowledge without the help
of a teacher.

Theory Driven Discovery - AM (1976)

 AM is a program that discovers concepts in elementary mathematics and set theory.
 AM has 2 inputs:
1. A description of some concepts of set theory (in LISP form).
 E.g. set union, intersection, the empty set.
2. Information on how to perform mathematics.
E.g. functions.

Given the above information AM discovered:

Integers
-- It is possible to count the elements of this set and this is an image of this counting function -- the
integers -- interesting set in its own right.

Addition
The union of two disjoints sets and their counting function.

Multiplication
Having discovered addition and multiplication as laborious set-theoretic operations more effective
descriptions were supplied by hand.

Prime Numbers
Factorization of numbers and numbers with only one factor were discovered.

Golbach's Conjecture
Even numbers can be written as the sum of 2 primes.
E.g. 28 = 17 + 11.

Maximally Divisible Numbers

 Numbers with as many factors as possible.
 A number k is maximally divisible is k has more factors than any integer less than k.
 E.g. 12 has six divisors 1,2,3,4,6,12.

How does AM work?

 AM employs many general-purpose AI techniques:
 A frame based representation of mathematical concepts.
 AM can create new concepts (slots) and fill in their values.
 Heuristic search employed
 250 heuristics represent hints about activities that might lead to interesting discoveries.

7
  How to employ functions, create new concepts, generalisation etc.
 Hypothesis and test based search.
 Agenda control of discovery process.

Data Driven Discovery -- BACON (1981)

 Many discoveries are made from observing data obtained from the world and making sense of it
o E.g. Astrophysics - discovery of planets, Quantum mechanics - discovery of sub-atomic particles.
 BACON is an attempt at provided such an AI system.
 BACON system outline:
 Starts with a set of variables for a problem.
o E.g. BACON was able able to derive the ideal gas law. It started with four variables p - gas pressure, V
-- gas volume, n -- molar mass of gas, T – gas temperature. Recall pV/nT = k where k is a constant.
 Values from experimental data from the problem are inputted.
 BACON holds some constant and attempts to notice trends in the data.
 Inferences made.
 BACON has also been applied to Kepler's 3rd law, Ohm's law, conservation of momentum and Joule's
law.

Common Sense

Synopsis
1. Introduction
2. Representing Qualitative information
3. Reasoning with qualitative information
4. Common sense Ontologies
5. Time
6. Space
7. Materials
8. Memory Organisation
9. Case Based Reasoning
Introduction
 True Intelligent systems exhibit common sense -- they possess more than enough knowledge to
be able to work in a given environment.
 Common sense systems need to support:
 Descriptions of everyday objects -- Frames.
 Typical sequences of everyday events -- Scripts.
 Default reasoning -- Nonmonotonic logics.

The Physical World -- Qualitative Physics

 Qualitative Physics is an area of AI concerned with reasoning about the behaviour of physical
systems.
 It is a good area to study since humans know a great deal about this world:
 They can predict that a falling ball will bounce many times.
 They can predict the projection of cricket ball and even catch it.
 They know a pendulum swings back and fore finally coming to rest in the middle.
 However most humans whilst being to operate in this world have no notion of the laws of physics
that govern this world.
 We can clearly look up the information and derive equations to describe, say pendulum motion.
 Indeed computers are very good at this sort of computation when they have been programmed
by experienced programmers.
 Is this how an intelligent system functions in this world?
 Three year old children can and cannot even read or do elementary maths?
 One other motivation is that whilst complex computer models can be assembled many problems

8
remain difficult or impossible to solve analytically.
 Systems of equations (differential etc.) might hard to derive and even impossible to solve.

Representing Qualitative information

 Qualitative physics seeks to understand physical processes by building models of them.
 A model may consist of the following entities:

Variables
-- make take on values as in a traditional physics model but with a restricted set of values, e.g.
temperature as

Quantity Spaces
-- a small set of discreet values for a variable.

Rate of Change
-- Variables take on different values at different times. A real valued rate of change can be modelled
qualitatively with a quantity space,
 e.g

Expressions
-- Combination of variables.

Equations
-- Assignment of expression to variables.

States
-- Sets of variables who's values change over time.
 Note that qualitative algebra is different: Say we

Reasoning with qualitative information

 Reasoning in this area is often called qualitative simulation.
 The basic idea being:
 Construct a sequence of discrete episodes that occur as qualitative variable value changes.
 States are linked by qualitative rules that may be general.
 Rules may be applied to many objects simultaneously as they may all influence each other --
constraint satisfaction used.
 Ambiguity may arise so split outcomes into different paths and form a network of all possible
states and transitions.
 Each path is called a history the network an envisionment.
 In order to achieve effective programs for this we must know how to represent the behavior of
many kinds of processes, materials and the world in which they act.

Common sense Ontologies

Time
 Here we address notions of time familiar to most people as opposed to the philosophical nature
of time.
 For instance
 Jimi Hendrix recorded albums between the mid 1960's and 1970.
 Jimi Hendrix died in 1970.
 Beautiful People released an album based on samples of all of Hendrix's recorded music.
 We can easily infer that Beautiful People's album was released after 1970.

9
The most basic notion of time is occupied by events:
 Events occur during intervals -- continuous spaces of time.
 An interval has a start and end point and a duration (of time) between them.
 Intervals can be related to one another -- descriptions such as is-before, is-after, meets, is met-
by, starts, is-started-by, during, contains, ends, is-ended-by and equals.
 We can build a axioms with intervals to describe events in time.

Space
 The Blocks World is a simple example of we can model and describe space.
 However common sense notions such a place object x near object y are not accommodated.
 Now objects have a spatial extent while events have a temporal extent.
 So we might try to extend of common sense theory of time.
 However space is 3D and there are many more relationships than those for time so it is not a
good idea.
 Another approach is view objects and space at various levels of abstraction.
 E.g. We can view most printed circuit boards as being a 2D object.
 Choosing a representation means selecting relevant properties at particular levels of
granularity.
 For instance we can define relations over spaces such as inside, adjacent etc.
 We can also define relations for curves, lines, surfaces, planes and volumes.
 E.g. along, across, perpendicular etc.

Materials
 We need to describe properties of materials:
 You cannot walk on water.
 If you knock a cup of coffee over what happens?
 If you pour a full kettle into a cup what happens?
 You can squeeze a sponge but not a brick.
 Liquids (as can be seen from above) provide many interesting points.
 It is useful to think of spaces occupied by objects. Thus we can define properties such as:
 Capacity -- a bound to an amount of liquid.
 Amount -- volume occupied by a liquid.
 Full -- if amount equals capacity.
 Other properties materials can posses include:
 Free -- if a space is not wholly contained inside another object.
 Surround -- if enclosed by a very thin free space.
 Rigid
 Flexible
 Particulate -- e.g. sand

Memory Organisation
 Memory is central to common sense behavior and also the basis for learning.
 Human memory is still not fully understood however psychologists have proposed several ideas:
 Short term memory (STM) -- only a few items at a time can be held here.
 Perceptual information stored directly here.
 Long term memory (LTM) -- capacity for storage is very large and fairly permanent

LTM is often divided up further:

 Episodic memory -- contains information about personal experiences.
 Semantic memory -- general facts with no personal meaning.
 E.g. Birds fly. Useful in natural language understanding.
 In terms of AI research work started by Quillian on semantic memory led to semantic networks
and frames and other slot and filler structures.

10
 Work on episodic memory grew out of scripts.
 Production systems are an example of STN-LTM computer models.

Case Based Reasoning

 Let us finish this topic by seeing how memory is employed in problem solving.
 We have seen that many problems are solved by analogy. Computer systems that perform this
 task are sometimes called case based reasoning (CBR) systems.
 CBR systems employ large case libraries rather than descriptions from first principles.
 They therefore rely heavily on memory organisation and retrieval.
 Σ A rich indexing system must be employed -- when reasoning with a problem only relevant
past experience should be recalled.
o Index by features present in problem.
 Require some measure of relevance of retrieved information.
o Some features only important in a certain context.
o Inductive and explanation based learning suitable here.
 The data structures used will be important as the number of cases represented will be large.
o Do we retrieve all information about a case or fragment of it?
 A number of cases are usually retrieved.
 We need to select the best one using some heuristic which may include:
o Goal directed preference -- cases that include same goal as current problem.
o Salient feature preference -- cases that include the most important (or largest number of)
features.
o Specificity preference -- certain match features identified.
o Frequency preference -- select frequently matched cases.
o Recency preference -- select recently matched cases.
o Ease of adaptation preference -- cases whose features easily modified for new problem.

Perception and Action

Synopsis
1. Introduction: What is perception in AI?
2. Figure: Autonomous Robot
3. For example:
4. Vision:
 Signal Processing:
 Measurement Analysis
 Pattern Recognition
 image Understanding
5. Speech Recognition
6. Speaker Dependence versus Speaker Independence:

Introduction: What is perception in AI?

 Perception is a process to interpret, acquire, select and then organize the sensory information that is
captured from the real world.
 For example: Human beings have sensory receptors such as touch, taste, smell, sight and hearing. So,
the information received from these receptors is transmitted to human brain to organize the received
information.
 According to the received information, action is taken by interacting with the environment to
manipulate and navigate the objects.
11
  Perception and action are very important concepts in the field of Robotics. The following figures
show the complete autonomous robot.

Figure: Autonomous Robot

 There is one important difference between the artificial intelligence program and robot. The AI
program performs in a computer stimulated environment, while the robot performs in the physical
world.

For example:
 In chess, an AI program can be able to make a move by searching different nodes and has no facility
to touch or sense the physical world.
 However, the chess playing robot can make a move and grasp the pieces by interacting with the
physical world.

Vision:
 Accurate machine vision opens up a new realm of computer applications. These applications include
mobile robot navigation, complex manufacturing tasks analysis of satellite images, and medical image
processing. The question is that how we can transform raw camera images into useful information about
the world.
 A Video Camera provides a computer with an image represented as a two-dimensional grid of intensity
levels. Each grid element, or pixel, may store a single bit of information (that is , black/white) or many
bits(perhaps a real-valued intensity measure and color information).
 A visual image is composed of thousands of pixels. What kinds of things might we want to do with such
an image? Here are four operations, in order of increasing complexity:

1. Signal Processing: - Enhancing the image, either for human consumption or as input to another
program.
2. Measurement Analysis: - For images containing a single object, determining the two dimensional
extent of the object depicted.
3. Pattern Recognition: - For single – object images, classifying the object into a category drawn from a
finite set of possibilities.
4. image Understanding :- For images containing many objects, locating the object in the image,
classifying them, and building a three-dimensional model of the scene.

12
Speech Recognition:
 Natural Language understanding systems usually accept typed input, but for a number of
applications this is not acceptable.
 Spoken language is a more natural form of communication in many human-computer interfaces.
Speech recognition systems have been available for some time, but their limitations have prevented
widespread used.
 The five major design issues in speech systems.
 These issues also provide dimensions along which systems can be compared with one another.

1. Speaker Dependence versus Speaker Independence:

 A speaker –independent system can liten to any speakear and translate the sounds into written text.
 Speaker independence is hard to achieve because of the wide variations in pitch and accent.
 It is easier to build a speaker –dependent system, which can be trained on the voice

Expert systems (ES)

Synopsis
1. Introduction
2. What are Expert Systems?
3. Capabilities of Expert Systems
4. Components of Expert Systems
 Knowledge Base
 Inference Engine
 User Interface
5. Applications of Expert System
6. Development of Expert Systems: General Steps
7. Limitations of Expert Systems
8. Advantages of Expert Systems:
9. Disadvantages of Expert Systems:

Introduction
 Expert systems (ES) are one of the prominent research domains of AI.
 It is introduced by the researchers at Stanford University, Computer Science Department.

What are Expert Systems?

 The expert systems are the computer applications developed to solve complex problems in a
particular domain, at the level of extra-ordinary human intelligence and expertise

Capabilities of Expert Systems

 The expert systems are capable of −

 Advising
 Instructing and assisting human in decision making
 Demonstrating
 Deriving a solution
 Diagnosing
 Explaining
 Interpreting input
 Predicting results
 Justifying the conclusion
 Suggesting alternative options to a problem

13
 They are incapable of −

 Substituting human decision makers

 Possessing human capabilities
 Producing accurate output for inadequate knowledge base
 Refining their own knowledge

Components of Expert Systems

The components of ES include −
1. Knowledge Base
2. Inference Engine
3. User Interface
Let us see them one by one briefly −

Knowledge Base
 It contains domain-specific and high-quality knowledge.
 Knowledge is required to exhibit intelligence.
 The success of any ES majorly depends upon the collection of highly accurate and precise knowledge.

What is Knowledge?
 The data is collection of facts.
 The information is organized as data and facts about the task domain.
 Data, information, and past experience combined together are termed as knowledge.

Components of Knowledge Base

 The knowledge base of an ES is a store of both, factual and heuristic knowledge.
 Factual Knowledge − It is the information widely accepted by the Knowledge Engineers and
scholars in the task domain.
 Heuristic Knowledge − It is about practice, accurate judgement, one’s ability evaluation, and
guessing.
Knowledge representation
 It is the method used to organize and formalize the knowledge in the knowledge base. It is in
the form of IF-THEN-ELSE rules.

Knowledge Acquisition
 The success of any expert system majorly depends on the quality, completeness, and accuracy

14
of the information stored in the knowledge base.
 The knowledge base is formed by readings from various experts, scholars, and the Knowledge
Engineers. The knowledge engineer is a person with the qualities of empathy, quick learning,
and case analyzing skills.
 He acquires information from subject expert by recording, interviewing, and observing him at
work, etc. He then categorizes and organizes the information in a meaningful way, in the form
of IF-THEN-ELSE rules, to be used by interference machine.
 The knowledge engineer also monitors the development of the ES.
Inference Engine
 Use of efficient procedures and rules by the Inference Engine is essential in deducting a correct,
flawless solution.
 In case of knowledge-based ES, the Inference Engine acquires and manipulates the knowledge
from the knowledge base to arrive at a particular solution.
 In case of rule based ES, it −
 Applies rules repeatedly to the facts, which are obtained from earlier rule application.
 Adds new knowledge into the knowledge base if required.
 Resolves rules conflict when multiple rules are applicable to a particular case.
 To recommend a solution, the Inference Engine uses the following strategies −
 Forward Chaining
 Backward Chaining

Forward Chaining
 It is a strategy of an expert system to answer the question, “What can happen next?”
 Here, the Inference Engine follows the chain of conditions and derivations and finally deduces the
outcome. It considers all the facts and rules, and sorts them before concluding to a solution.
 This strategy is followed for working on conclusion, result, or effect. For example, prediction of share
market status as an effect of changes in interest rates.

Backward Chaining
 With this strategy, an expert system finds out the answer to the question, “Why this happened?”
 On the basis of what has already happened, the Inference Engine tries to find out which conditions
could have happened in the past for this result. This strategy is followed for finding out cause or reason.
For example, diagnosis of blood cancer in humans.

15
 User Interface
 User interface provides interaction between user of the ES and the ES itself. It is generally
 Natural Language Processing so as to be used by the user who is well-versed in the task domain.
 The user of the ES need not be necessarily an expert in Artificial Intelligence.
 It explains how the ES has arrived at a particular recommendation.
 The explanation may appear in the following forms −
 Natural language displayed on screen.
 Verbal narrations in natural language.
 Listing of rule numbers displayed on the screen.

Requirements of Efficient ES User Interface

 It should help users to accomplish their goals in shortest possible way.
 It should be designed to work for user’s existing or desired work practices.
 Its technology should be adaptable to user’s requirements; not the other way round.
 It should make efficient use of user input.

Applications of Expert System

 The following table shows where ES can be applied.

Application Description

Design Domain Camera lens design, automobile design.

Diagnosis Systems to deduce cause of disease from observed data,

Medical Domain
conduction medical operations on humans.

Comparing data continuously with observed system or with prescribed

Monitoring Systems behavior such as leakage monitoring in long petroleum pipeline.

Process Control
Controlling a physical process based on monitoring.
Systems

16
 Knowledge Domain Finding out faults in vehicles, computers.

Detection of possible fraud, suspicious transactions, stock market

Finance/Commerce
trading, Airline scheduling, cargo scheduling.

Expert System Technology

There are several levels of ES technologies available. Expert systems technologies include −
 Expert System Development Environment − The ES development environment includes hardware
and tools. They are −
o Workstations, minicomputers, mainframes.

o High level Symbolic Programming Languages such as LISt Programming (LISP) and PROgrammation
en LOGique (PROLOG).
o Large databases.

 Tools − They reduce the effort and cost involved in developing an expert system to large extent.
o Powerful editors and debugging tools with multi-windows.

o They provide rapid prototyping

o Have Inbuilt definitions of model, knowledge representation, and inference design.

 Shells − A shell is nothing but an expert system without knowledge base. A shell provides the
developers with knowledge acquisition, inference engine, user interface, and explanation facility. For
example, few shells are given below −
o Java Expert System Shell (JESS) that provides fully developed Java API for creating an expert system.

o Vidwan, a shell developed at the National Centre for Software Technology, Mumbai in 1993. It enables
knowledge encoding in the form of IF-THEN rules.

Development of Expert Systems: General Steps

The process of ES development is iterative. Steps in developing the ES include −

Identify Problem Domain

 The problem must be suitable for an expert system to solve it.
 Find the experts in task domain for the ES project.
 Establish cost-effectiveness of the system.
Design the System
 Identify the ES Technology
 Know and establish the degree of integration with the other systems and databases.
 Realize how the concepts can represent the domain knowledge best.
Develop the Prototype
From Knowledge Base: The knowledge engineer works to −
 Acquire domain knowledge from the expert.
 Represent it in the form of If-THEN-ELSE rules.
Test and Refine the Prototype
17
18
  The knowledge engineer uses sample cases to test the prototype for any deficiencies in performance.
 End users test the prototypes of the ES.
Develop and Complete the ES
 Test and ensure the interaction of the ES with all elements of its environment, including end users,
databases, and other information systems.
 Document the ES project well.
 Train the user to use ES.
Maintain the System
 Keep the knowledge base up-to-date by regular review and update.
 Cater for new interfaces with other information systems, as those systems evolve.

Limitations of Expert Systems:

 Don’t have human-like decision making power.
 Can’t possess human capabilities.
 Can’t produce correct result from less amount of knowledge.
 Requires excessive training.

Advantages of Expert Systems:

 Low accessibility cost.
 Fast response.
 Not affected by emotions unlike humans.
 Low error rate.
 Capable of explaining how they reached a solution.

Disadvantages of Expert Systems:

 Expert system have no emotions.
 Common sense is the main issue of the expert system.
 It is developed for a specific domain.
 It needs to be updated manually. It does not learn itself.
 Not capable to explain the logic behind the decision.

All the best..

19