Artificial Intelligence

Definition:
Artificial Intelligence (AI) refers to the development of computer systems of
performing tasks that require human intelligence.
The ultimate goal of AI is to create machines that can emulate capabilities and
carry out diverse tasks, with enhanced efficiency and precision. The field of AI
holds potential to revolutionize aspects of our daily lives.

Approaches of Artificial Intelligence Learning: -

1. Acting humanly – The Turing Test approach
2. Thinking Humanly: The Cognitive Modelling Approach
3. Thinking Rationally Laws of Thought Approach
4. Acting Rationally

[Link] humanly – The Turing Test approach

The Turing Test was designed to provide a satisfactory operational definition of
intelligence and proposed by Alan Turing (Turing 1950). Turing defined that the
ability to achieve human-level performance in all cognitive tasks, which is
sufficient to fool an interrogator is Intelligence of Machine. The test Turing
proposed is that the computer should be interrogated by a human via a teletype,
and passes the test if the interrogator cannot tell if there is a computer or human
at the other end.
Programming a computer to pass the test provides plenty to work on and also
requires the following capabilities.
Natural Language Processing to enable It to communicate successfully in English
(or some other human language)
Knowledge Representation to store information provided before or during the
interrogator,
Automated Reasoning to use the stored information to answer question. and to
draw new conclusions,
Machine Learning to adapt to nest circumstances and to detect and extrapolate
patterns
Even though Total Turing test deliberately avoided direct physical interaction
between the interrogator and the computer but includes a video signal so that
the interrogator can test the subject’s perceptual abilities, as well as the
opportunity for the interrogator pass physical objects “through the hatch”.
To pass the total Turing test the compute will need
• Computer Vision to perceive objects, and
• Robotics to move them about.
Within AI, there has not been a big effort to try to pass the Turing test.

[Link] Humanly: The Cognitive Modelling Approach: -

Cognitive science is the interdisciplinary study of mind and intelligence, e
mbracing philosophy, psychology, artificial intelligence, neuroscience, linguis
tics, and anthropology.
The interdisciplinary field of cognitive science brings together computer m
odels from Artificial Intelligence and experimental techniques from cognitive
psychology to try to construct precise and testable theories of the workin
gs of the human mind. And if we are going to say that a given program think
s like a human being, we must have some way of determining how human b
eings think. For that, we need to get inside the actual workings of the hu
man mind.
[Link] Rationally Laws of Thought Approach: -
The rational thinking approach in AI is based on the assumption that our minds
operate according to the laws of thought. This approach uses techniques like
syllogisms, which provide Patterns for argument structures. It aims to design
intelligent systems that can make correct inferences based on given premises.
Syllogisms are logical forms that consist of two premises and a conclusion. They
serve as a framework for drawing correct conclusions from provided premises.
For example, the syllogism "Socrates is a man" and "All men are mortal" leads us
to the conclusion that "Socrates is mortal." To illustrate the concept of syllogism,
let's consider the example provided earlier: "Socrates is a man" and "All men are
mortal." From these two premises, we can infer that Socrates is mortal. This
inference is based on the fact that Socrates is a man, and all men are mortal.
Despite its appeal, the rational thinking approach faces two significant obstacles.
Firstly, representing uncertain knowledge in the formal terms required by logical
notation is challenging. Humans often make decisions without feeling 100%
certain, making it difficult to model such informal knowledge in a formal
framework. Secondly, even with programs capable of drawing conclusions from
given premises, the computational resources required can quickly become
overwhelming when dealing with a large number of sentences and possible
combinations.
[Link] Rationally: -
In the acting rationally approach, AI is defined as the design of computer
programs that act autonomously, perceive from the environment, persist over
time, adapt to change, and pursue goals. This definition goes beyond mere
computation and focuses on creating intelligent systems that can achieve
outcomes. A rational agent in AI is one that acts with the intention of achieving
the best outcome among all possible outcomes. It operates based on the
principle of maximizing expected utility while taking into account uncertainty
and the available options. Rational agents strive to achieve the best possible
outcome given the available options and the uncertainties surrounding them.
They consider the consequences of their actions and choose the option that is
expected to yield the most favourable outcome.

Foundations of AI: -
[Link] Learning
[Link] Systems
[Link] Vision
[Link] Language Processing
[Link]
[Link] Learning: -
Machine learning (ML) is the science of empowering machines to make decisions
without human intervention. This sub-discipline forms the backbone of AI,
enabling computers to learn and interpret patterns in images, sounds, and
structured data using multidimensional arrays. ML is further subdivided into four
types of learning:
Supervised learning: Given an array of features (i.e., week of the year, price, etc.)
and a labeled output variable (e.g., sales), predict the best possible estimate of
the label variable given some new input array.
Unsupervised learning: Given an array of features (e.g., demographic
information, ZIP code, etc.), expose and visualize hidden relationships and
anomalies within the array.
Semi-supervised: Given an array of features and a limited quantity of some
labeled output variable, predict the best possible estimates for the missing label
variables.
Reinforcement learning: Given some objective, train an artificial agent to
maximize its utility according to some user-defined utility function.
[Link] Systems: -
An expert system (ES) is an artificial agent which leverages pre-programmed
knowledge to offer advice or make decisions. Though expert systems don’t enjoy
the same hype as machine learning, there are many reasons why we might prefer
an ES over ML:
An expert system can take advantage of human insights discovered through trial
and error
Expert systems are more predictable and are less likely to make extreme
errors when faced with previously-unseen inputs
Expert systems have historically been faster and easier to implement, though ML
has become much more accessible in recent years
[Link] Vision: -
Computer vision (CV) is the automatic extraction, analysis, and interpretation of
images or videos. CV converts photos and videos into numerical arrays, enabling
ML algorithms to draw inferences, make predictions, and even generate new
images based on user-defined inputs. Potential uses for CV have been studied
for decades, but CV has only recently become possible at scale thanks to three
innovations:
More efficient algorithms: Deep learning (convolutional neural networks,
specifically) significantly reduces the memory footprint and computational
runtime of CV tasks.
Better computing resources: GPU improvements, distributed architectures (e.g.,
Spark), and the availability of inexpensive cloud computing resources have made
it cheaper than ever to run memory-hungry CV algorithms.
Availability of images to train on: The proliferation of social media platforms,
community forums, and digital / mobile cameras have drastically increased the
number of publicly-available images that can be used to train CV algorithms.
These three innovations have opened the floodgates for new CV use cases,
including self-driving cars and automated retailers (e.g., Amazon Go).
[Link] Language Processing: -
Natural language processing (NLP) is the automatic extraction, analysis, and
generation of human language. NLP algorithms parse sentences in various ways
(e.g., splitting by word, splitting by letter, reading both left-to-right and right-to-
left, etc.) to automatically draw inferences about the writer’s meaning and
intent. NLP’s various use cases include:
• Named entity recognition and conference resolution
• Part-of-speech tagging
• Reading comprehension & question answering
• Machine translation
• Text summarization & topic modeling
• Spellcheck & autocomplete
Like CV, NLP has come a long way over the past decade thanks to innovations in
deep learning that have made it faster and easier to train ML models on human
language. In the past, engineers would spend hours examining, filtering, and
transforming text to avoid computational bottlenecks. Siri and Alexa are great
examples of NLP in action
5. Robotics: -
Robotics is the science of designing, constructing, operating, and applying
robots to solve human problems. Most robots rely on expert systems to
accomplish their objective, but the robots of tomorrow will become
exponentially more useful by incorporating machine learning, computer vision,
and natural language processing into their operating systems.

History of AI: -
Fundamentally, Artificial Intelligence is the process of building machines that can
replicate human intelligence. These machines can learn, reason, and adapt while
carrying out activities that normally call for human intelligence. With artificial
intelligence (AI) this world of natural language comprehension, image
recognition, and decision making by computers can become a reality.
The Dawn of Artificial Intelligence (1950s-1960s)
The 1950s , which saw the following advancements , are considered to be the
birthplace of AI :
• 1950 : In 1950 saw the publication of Alan Turing’s work ,“Computing
Machinery and Intelligence “ which introduced the Turing Test—a
measure of computer intelligence.
• 1956: A significant turning point in AI research occurs in 1956 when, John
McCarthy first uses the phrase “Artificial Intelligence” at the Dartmouth
Workshop.
• 1950s–1960s: The goal of early artificial intelligence (AI) research was to
encode human knowledge into computer programs through the use of
symbolic reasoning, and logic-based environments.
• Limited Advancement: Quick advances are hampered by limited resources
and computing-capacity.
• Early AI systems: This made an effort to encode human knowledge
through the use of logic, and symbolic thinking. The development of early
artificial intelligence (AI) systems that, depended on symbolic thinking and
logic was hampered by a lack of resources, and processing capacity , which
caused the field to advance slowly in the beginning.
AI’s Early Achievements and Setbacks (1970s-1980s)
This age has seen notable developments as well as difficulties :
 • 1970: The 1970s witnessed the development of expert systems , which
were intended to capture the knowledge of experts in a variety of
domains. Data Scientists created rule-based systems that , could use pre-
established guidelines to address certain issues.
• Limitations: Due to their inability to handle ambiguity and complicated
circumstances , these systems had a limited range of applications.
• The Artificial Intelligence Winter(1970–1980): A period of inactivity
brought on by a lack of funding , and un-met expectations.
Machine Learning and Data-Driven Approaches (1990s)
The 1990s bring a transformative move in AI :
• 1990s: A worldview move towards machine learning approaches happens.
• Rise of Machine-Learning: Calculations learn from information utilizing
strategies like neural systems, choice trees , and bolster vector machines.
• Neural Organize Insurgency: Propelled by the human brain, neural
systems pick up ubiquity for errands like discourse acknowledgment, stock
advertise expectation , and motion picture suggestions.
• Information Powers AI: Expanded handling control , and information
accessibility fuel the development of data driven AI.
• Unused Areas Rise: Proposal frameworks , picture acknowledgment and
normal dialect handling (NLP) take root.
• Brilliant Age of AI: AI frameworks exceed expectations in dis-course
acknowledgment, stock determining, and suggestion frameworks.
• Improved Execution: Handling control enhancements and information
accessibility drive progressions.
The AI Boom: Deep Learning and Neural Networks (2000s-2010s)
The 21st century , witnesses the rise of profound learning , and neural systems :
• 2000s-2010s: Profound learning a subset of machine learning imitating
the human brain’s structure and work , came to the cutting edge.
• Profound Neural Systems: Multi-layered neural systems exceeded
expectations in ranges such as – picture acknowledgment, NLP and
gaming.
 • Innovative Progressions: Profound learning encouraged advance in
discourse acknowledgment, NLP , and computer vision.
• Corporate Speculation: Tech monsters like Facebook, Google , and
OpenAI made noteworthy commitments to AI inquire about.
• Counterfeit Neural Systems: Complex calculations, based on
interconnected neurons control profound learning headways.
Generative Pre-trained Transformers: A New Era (GPT Series)
A novel advancement in recent times is the use of Generative Pre-trained
Transformers :
• GPT Series: Trained on enormous volumes of textual data , these models
have rocked the globe.
• GPT-3: This model transforms language processing by producing writing
that is similar to that of a human being and translating between
languages.
• Learning from Text: Large volumes of text are absorbed by GPT models,
such as – GPT-3, which help them comprehend syntax, context , and
comedy.
• Beyond Translation: GPT-3 serves as a portable writing assistant by
producing essays, poetry , and even language translations.
• The Upcoming Generation: This new wave of models , which can write,
translate and generate original material as well as provide insightful
responses, is exemplified by models such as Bard, ChatGPT, and Bing
Copilot.
• Pushing Boundaries: These developments have increased the possible
applications of AI showcasing its ability in content production, creative
projects and language translation.
• The Future of AI: Predictions and Trends
• AI has a plethora of exciting prospects that beyond our wildest
expectations. In addition to, learning and problem-solving artificial
intelligence (AI) systems should be able to reason complexly, come up with
original solutions and meaningfully engage with the outside world.
Consider an AI – Doctor that is able to recognize and feel the emotions of
a patient in addition to diagnosing ailments.
 • There are obstacles in the way of this future , though. Professionals are
already pondering the ethical implications of advanced artificial
intelligence. There is hope for a future in which AI and humans work
together productively enhancing each other advantages. The future is full
with possibilities , but responsible growth and careful preparation are
needed.

AI Techniques: -
• Artificial Intelligence techniques refer to a set of methods and algorithms
used to develop intelligent systems that can perform tasks requiring
human-like intelligence. Some of the widely used ones are:
• Machine Learning.
• Natural Language Processing.
• Computer Vision.
• Deep Learning
• Data Mining
• Robotics.
• Machine Learning:

•
• This approach involves the building of algorithms to learn patterns in data
and make predictions based on it.
• 1. Unsupervised machine learning -AI systems analyse unlabelled data,
where no predefined outcomes are provided. The objective is to uncover
inherent structures or patterns within the data without any prior
knowledge. For instance, it can group similar customer behaviour data to
identify customer segments for targeted marketing strategies.
• 2. Supervised learning – A combination of an input data set and the
intended output is inferred from the training data. AI systems learn from
a labelled dataset, where each data point is associated with a known
outcome. For instance, it enables email spam filters to distinguish
between spam and legitimate emails based on learned patterns.
• 3. Semi-supervised learning – It is a method that uses a small amount of
labelled data and a large amount of unlabelled data to train a model. The
goal of semi-supervised learning is to learn a function that can accurately
 predict the output variable based on the input variables, similar to
supervised learning. However, unlike supervised learning, the algorithm is
trained on a dataset that contains both labelled and unlabelled data.
• 4. Reinforcement learning – In RL, the data is accumulated from machine
learning systems that use a trial-and-error method to learn from
outcomes and decide which action to take next. After each action, the
algorithm receives feedback that helps it determine whether the choice it
made was correct, neutral or incorrect. It performs actions with the aim
of maximizing rewards, or in other words, it is learning by doing in order
to achieve the best outcomes.
• Natural Language Processing:
• Natural Language Processing involves programming computers to process
human languages to facilitate interactions between humans and
computers.
• However, the nature of human languages makes Natural Language
Processing difficult because of the rules involved in passing information
using natural language. NLP leverages algorithms to recognize and
abstract the rules of natural languages, converting unstructured human
language data into a computer-understandable format.

•
• Applications of Natural Language Processing can be found in IVR systems
and applications used in call centres, language translation applications like
Google Translate, and word processors such as Microsoft Word to check
the accuracy of grammar in text.
• This AI technique has paved the way for virtual assistants, chatbots, and
language translation tools, making communication between humans and
machines more seamless than ever.
• Some of the common variants of NLP are:
• 1. Lexical integration – Lexical analysis is the process of converting a
sequence of characters into a sequence of tokens. A lexer is generally
 combined with a parser, which together analyses the syntax of
programming languages, web pages, and so forth. Lexers and parsers are
most often used for compilers. The text or sound waves are segmented
into words and other units.
• 2. Syntactic integration – Syntactic analysis is the process of analysing a
string of symbols, either in natural language, computer languages, or data
structures, conforming to the rules of formal grammar. It is used in the
analysis of computer languages, to facilitate the writing of compilers and
interpreters. Grammatical rules are applied to categories and groups of
words, not individual words. It is a crucial part of NLP.
• 3. Semantic integration – Semantic Analysis attempts to understand the
meaning of the human language. It captures the meaning of the given text
while considering context, logical structuring of sentences, and grammar
roles.
• 2 parts of Semantic Analysis are:
• Lexical Semantic Analysis
• Compositional Semantics Analysis.
• 4. Pragmatic integration – Pragmatic Analysis is part of the process of
extracting information from text. It focuses on taking a structured set of
text and figuring out the actual meaning of the text. It also focuses on the
meaning of the words of the time and context.
• Effects on interpretation can be measured using PA by understanding the
communicative and social content from the given text.
• 5. Disclosure integration – Discourse analysis is used to uncover the
motivation behind a text and is useful for studying the underlying meaning
of a spoken or written text as it considers the social and historical contexts
of it. Discourse analysis is a process of performing text or language
analysis, that involves text interpretation and an understanding of social
interactions and customs.
• Computer Vision:
• Computer Vision equips machines with the ability to interpret visual
information from the world. This technique has revolutionized industries
like healthcare, automotive, and robotics, enabling tasks such as facial
recognition, object detection, and autonomous driving. The extent to
which it can discriminate between objects is an essential component of
machine vision.
• Sensitivity in computer vision is an AI application’s ability to pick out small
details in visual information. A low-sensitivity system may not pick up
subtle clues in images or fail to work well in low lighting. However, high
 sensitivity might be able to look at an image’s fine details and pick up on
information other systems might miss.
• Sensitivity in computer vision is an AI application’s ability to pick out small
details in visual information. A low-sensitivity system may not pick up
subtle clues in images or fail to work well in low lighting. However, high
sensitivity might be able to look at an image’s fine details and pick up on
information other systems might miss. A common example is Surveillance
systems.
• Resolution is the level of detail a computer vision system can capture and
process. High-resolution images are vital for correctly identifying an
image’s detail.
• Robotics & Automation:
• Automation aims to enable machines to perform boring, repetitive jobs,
increasing productivity and delivering more effective, efficient, and
affordable results. To automate processes, many businesses employ
machine learning, artificial neural, and graphs.
• By leveraging the CAPTCHA technique, this automation can avoid fraud
problems during online payments.
• Robotic process automation is designed to carry out high-volume,
repetitive jobs while being capable of adapting to changing conditions.

• Deep Learning:
Deep learning is the branch of machine learning which is based on artificial
neural network architecture. An artificial neural network or ANN uses
layers of interconnected nodes called neurons that work together to
process and learn from the input data.

• In a fully connected Deep neural network, there is an input layer and one
or more hidden layers connected one after the other. Each neuron
receives input from the previous layer neurons or the input layer. The
output of one neuron becomes the input to other neurons in the next
layer of the network, and this process continues until the final layer
produces the output of the network. The layers of the neural network
 transform the input data through a series of nonlinear transformations,
allowing the network to learn complex representations of the input data.
• The main applications of deep learning can be divided into computer
vision, natural language processing (NLP), and reinforcement learning.
• In computer vision, Deep learning models can enable machines to identify
and understand visual data. Some of the main applications include the
identification and locating of objects within images and videos.
• In NLP, the Deep learning model can enable machines to understand and
generate human language. Some of the main applications include the
generation of essays, translating languages, and sentiment analysis
• In reinforcement learning, deep learning works as training agents to take
action in an environment to maximize a reward. Some of the main
applications of deep learning in reinforcement learning include the
training of robots to perform complex tasks such as grasping objects,
navigation, and manipulation.
• Data Mining:
• Data mining is the process of extracting knowledge or insights from large
amounts of data using various statistical and computational techniques.
The data can be structured, semi-structured, or unstructured, and can be
stored in various forms such as databases, data warehouses, and data
lakes.
• The primary goal of data mining is to discover hidden patterns and
relationships in the data that can be used to make informed decisions or
predictions. This involves exploring the data using various techniques such
as clustering, classification, regression analysis, association rule mining,
and anomaly detection.
• Data mining has a wide range of applications across various industries,
including marketing, finance, healthcare, and telecommunications. For
example, in marketing, data mining can be used to identify customer
segments and target marketing campaigns, while in healthcare, it can be
used to identify risk factors for diseases and develop personalized
treatment plans.
• However, data mining also raises ethical and privacy concerns, particularly
when it involves personal or sensitive data. It’s important to ensure that
data mining is conducted ethically and with appropriate safeguards in
place to protect the privacy of individuals and prevent misuse of their
data.
Expert System: -
• An expert system is a computer program that is designed to solve complex
problems and to provide decision-making ability like a human expert. It
performs this by extracting knowledge from its knowledge base using the
reasoning and inference rules according to the user queries.
• The expert system is a part of AI, and the first ES was developed in the
year 1970, which was the first successful approach of artificial intelligence.
It solves the most complex issue as an expert by extracting the knowledge
stored in its knowledge base. The system helps in decision making for
compsex problems using both facts and heuristics like a human expert. It
is called so because it contains the expert knowledge of a specific domain
and can solve any complex problem of that particular domain. These
systems are designed for a specific domain, such as medicine, science, etc.
• The performance of an expert system is based on the expert's knowledge
stored in its knowledge base. The more knowledge stored in the KB, the
more that system improves its performance. One of the common
examples of an ES is a suggestion of spelling errors while typing in the
Google search box.
• Below is the block diagram that represents the working of an expert
system:

• Characteristics of Expert System

• High Performance: The expert system provides high performance for
solving any type of complex problem of a specific domain with high
efficiency and accuracy.
• Understandable: It responds in a way that can be easily understandable
by the user. It can take input in human language and provides the output
in the same way.
• Reliable: It is much reliable for generating an efficient and accurate
output.
• Highly responsive: ES provides the result for any complex query within a
very short period of time.
• Components of Expert System
• An expert system mainly consists of three components:
• User Interface
• Inference Engine
• Knowledge Base

•
1. User Interface
• With the help of a user interface, the expert system interacts with the user,
takes queries as an input in a readable format, and passes it to the
inference engine. After getting the response from the inference engine, it
displays the output to the user. In other words, it is an interface that helps
a non-expert user to communicate with the expert system to find a
solution.
2. Inference Engine(Rules of Engine)
• The inference engine is known as the brain of the expert system as it is the
main processing unit of the system. It applies inference rules to the
knowledge base to derive a conclusion or deduce new information. It
helps in deriving an error-free solution of queries asked by the user.
• With the help of an inference engine, the system extracts the knowledge
from the knowledge base.
• There are two types of inference engine:
• Deterministic Inference engine: The conclusions drawn from this type of
inference engine are assumed to be true. It is based on facts and rules.
• Probabilistic Inference engine: This type of inference engine contains
uncertainty in conclusions, and based on the probability.
• Inference engine uses the below modes to derive the solutions:
• Forward Chaining: It starts from the known facts and rules, and applies
the inference rules to add their conclusion to the known facts.
• Backward Chaining: It is a backward reasoning method that starts from
the goal and works backward to prove the known facts.
3. Knowledge Base
• The knowledgebase is a type of storage that stores knowledge acquired
from the different experts of the particular domain. It is considered as big
storage of knowledge. The more the knowledge base, the more precise
will be the Expert System.
• It is similar to a database that contains information and rules of a
particular domain or subject.
• One can also view the knowledge base as collections of objects and their
attributes. Such as a Lion is an object and its attributes are it is a mammal,
it is not a domestic animal, etc.
• Components of Knowledge Base
• Factual Knowledge: The knowledge which is based on facts and accepted
by knowledge engineers comes under factual knowledge.
• Heuristic Knowledge: This knowledge is based on practice, the ability to
guess, evaluation, and experiences.
• Knowledge Representation: It is used to formalize the knowledge stored
in the knowledge base using the If-else rules.
Knowledge Acquisitions: It is the process of extracting, organizing, and
structuring the domain knowledge, specifying the rules to acquire the
knowledge from various experts, and store that knowledge into the
knowledge base.
Below are the points that are describing the need of the ES:
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.
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.
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
• Not affected by emotions: These systems are not affected by human
emotions such as fatigue, anger, depression, anxiety, etc.. Hence the
performance remains constant.
• High security: These systems provide high security to resolve any query.
• 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.
• 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.
Capabilities of the Expert System
Below are some capabilities of an Expert System:
• Advising: It is capable of advising the human being for the query of any
domain from the particular ES.
• Provide decision-making capabilities: It provides the capability of decision
making in any domain, such as for making any financial decision, decisions
in medical science, etc.
• Demonstrate a device: It is capable of demonstrating any new products
such as its features, specifications, how to use that product, etc.
• Problem-solving: It has problem-solving capabilities.
• Explaining a problem: It is also capable of providing a detailed description
of an input problem.
• Interpreting the input: It is capable of interpreting the input given by the
user.
• Predicting results: It can be used for the prediction of a result.
• Diagnosis: An ES designed for the medical field is capable of diagnosing a
disease without using multiple components as it already contains various
inbuilt medical tools.
Advantages of Expert System
• These systems are highly reproducible.
• They can be used for risky places where the human presence is not safe.
• Error possibilities are less if the KB contains correct knowledge.
• The performance of these systems remains steady as it is not affected by
emotions, tension, or fatigue.
• They provide a very high speed to respond to a particular query.
Limitations of Expert System
• The response of the expert system may get wrong if the knowledge base
contains the wrong information.
• Like a human being, it cannot produce a creative output for different
scenarios.
• Its maintenance and development costs are very high.
• Knowledge acquisition for designing is much difficult.
• For each domain, we require a specific ES, which is one of the big
limitations.
• It cannot learn from itself and hence requires manual updates.
• Applications of Expert System
• It can be broadly used for designing and manufacturing physical devices
such as camera lenses and automobiles.
• These systems are primarily used for publishing the relevant knowledge
to the users. The two popular ES used for this domain is an advisor and a
tax advisor.
• In the finance industries, it is used to detect any type of possible fraud,
suspicious activity, and advise bankers that if they should provide loans for
business or not.
• In medical diagnosis, the ES system is used, and it was the first area where
these systems were used.
• The expert systems can also be used for planning and scheduling some
particular tasks for achieving the goal of that task.