Expert System - 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. Characteristics of Expert Systems
• High performance • Understandable • Reliable • Highly responsive
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
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 − • Knowledge Base • Inference Engine • User Interface

A blackboard system, in the context of artificial intelligence and knowledge representation, refers to a computer-based
system designed to simulate human problem-solving and reasoning processes. The concept is inspired by the traditional
classroom blackboard where information is presented, updated, and accessed by multiple users. In the context of AI, the
blackboard system serves as a shared knowledge base that various specialized problem-solving modules can access and
contribute to.

Modularity: A blackboard system is typically modular, consisting of multiple independent knowledge sources or modules.
These modules, often referred to as experts or agents, focus on specific aspects of the problem domain. Shared Knowledge
Base (Blackboard): The central component of a blackboard system is the blackboard itself, which acts as a shared memory
space. It contains the current state of the problem, relevant data, and intermediate results. Asynchronous Processing:
Modules in a blackboard system operate independently and asynchronously. They can examine the current state of the
blackboard, make inferences, and update the blackboard with new information. This allows for flexible and parallel
problem-solving. Collaborative Problem Solving: The blackboard system promotes collaborative problem-solving by
enabling different modules to contribute their expertise to the solution. As each module processes information and updates
the blackboard, other modules can respond to those changes and adapt their own reasoning accordingly.

Areas of Expert systems - Expert systems are computer programs that emulate the decision-making ability of a human
expert in a specific domain. These systems are designed to solve complex problems by reasoning through a knowledge base
of human expertise. Expert systems find applications in various fields, and their use has evolved over time. Natural
Language Processing: [Link] Translation: Expert systems use natural language processing to facilitate language
translation and interpretation. [Link]: They enable interactive conversations with users to provide information and
answer queries. Education: 1. Intelligent Tutoring Systems: Expert systems are used in educational settings to provide
personalized tutoring and adaptive learning experiences. [Link] Grading: They help automate the grading process
for assignments and exams. Customer Support: 1. Troubleshooting: Expert systems are used in customer support to
diagnose technical issues and provide solutions. [Link] Recommendations: They assist in recommending products or
services based on customer preferences and needs.

Bayes' Theorem is a fundamental concept in probability theory that describes the probability of an event based on prior
knowledge of conditions related to the event. It is named after the Reverend Thomas Bayes, who introduced the theorem.
The formula for Bayes' Theorem is as follows:
Joint probability and conditional probability are concepts in probability theory that describe the likelihood of events
occurring under certain conditions.

Membership functions play a crucial role in fuzzy logic by determining the degree of membership of an element in a fuzzy
set. Here are six types of commonly used membership functions in fuzzy logic
Triangular Membership Function: This is a simple and commonly used triangular-shaped membership function. It has three
parameters: a lower limit, a peak or modal value, and an upper limit. • Trapezoidal Membership Function:Similar to the
triangular membership function, the trapezoidal membership function has four parameters: a lower limit, a left base, a right
base, and an upper limit. It is shaped like a trapezoid. • Gaussian Membership Function:The Gaussian membership function
is bell-shaped and is defined by a mean (peak) and a standard deviation. It resembles a normal distribution curve. •
Sigmoidal (S-shaped) Membership Function:Sigmoidal membership functions have an S-shaped curve and are often used in
fuzzy systems. They are defined by parameters that control the slope and shape of the curve. • Generalized Bell
Membership Function:The generalized bell membership function is a versatile function that includes the Gaussian and
triangular membership functions as special cases. It is defined by parameters that control the width, slope, and center of
the bell curve. • Piecewise Linear Membership Function:This type of membership function consists of linear segments. It is
more flexible than other functions and can approximate various shapes by combining straight-line segments.

Clustering • Cluster analysis, or clustering, is an unsupervised machine learning task. It involves automatically discovering
natural grouping in data. • Unlike supervised learning (like predictive modeling), clustering algorithms only interpret the
input data and find natural groups or clusters in feature space. • Clustering is the assignment of a set of observations into
subsets (called clusters) so that observations in the same cluster are similar in some sense. • Clustering is a method of
unsupervised learning, and a common technique for statistical data analysis used in many fields
Artificial Neural Network? • Artificial Neural Network (ANN) is an efficient computing system whose central theme is
borrowed from the analogy of biological neural networks. • ANNs are also named as “artificial neural systems,” or “parallel
distributed processing systems,” or “connectionist systems.” • ANN acquires a large collection of units that are
interconnected in some pattern to allow communication between the units. • These units, also referred to as nodes or
neurons, are simple processors which operate in parallel. • Every neuron is connected with other neuron through a
connection link. • Each connection link is associated with a weight that has information about the input signal. • This is the
most useful information for neurons to solve a particular problem because the weight usually excites or inhibits the signal
that is being communicated. • Each neuron has an internal state, which is called an activation signal. • Output signals, which
are produced after combining the input signals and activation rule, may be sent to other units

• Machine learning is the brain where all the learning takes place. The way the machine learns is similar to the human
being. Humans learn from experience. The more we know, the more easily we can predict. • By analogy, when we face an
unknown situation, the likelihood of success is lower than the known situation. • Machines are trained the same. To make
an accurate prediction, the machine sees an example. When we give the machine a similar example, it can figure out the
outcome. However, like a human, if its feed a previously unseen example, the machine has difficulties to predict. • The core
objective of machine learning is the learning and inference. • First of all, the machine learns through the discovery of
patterns. This discovery is made thanks to the data. One crucial part of the data scientist is to choose carefully which data to
provide to the machine. • The list of attributes used to solve a problem is called a feature vector. You can think of a feature
vector as a subset of data that is used to tackle a problem

Single Layer Feed-Forward Neural Network

Layer is formed by taking processing element & combining it with other processing element. • Input & output are linked
with each other. • Inputs are connected to the processing nodes with various weights resulting series of output one per
node. • Zero hidden layers are present. • Not efficient in certain areas.
Multi Layer Feed-Forward Neural Network
It is formed by interconnection of several layers. • There are multiple layers between input & output layers which are
known as hidden layers. • Input layers receives input & buffers input signal, output layer generates output. • Zero to
several hidden layers are in a network. • More the hidden layers, more the complexity of networks, but efficient output is
produced. •
Single-Agent System
In a single-agent system, an agent models itself, the environment, and their interactions. On the other hand, in a multi-
agent system, the agents are independent entities with their own goals, actions, and knowledge. Even though an agent in a
single-agent system is part of an environment, the other agents sitting in the environment are not recognized by the agent
and they are just considered to be part of that environment too. a single-agent system, where the agent possesses goals,
actions, and domain knowledge. Its sensors and effectors are connected to the environment.

Multi-Agent Systems
Multi-agent systems (MAS) are referred to as systems consisting of software agents. The agents in a multi-agent system
could also be humans or robots. However, we are concerned with multiple interacting intelligent agents that are used to
solve problems which are difficult or impossible for an individual agent to solve. The agents in a multi-agent system have
several important characteristics such as autonomy. Every agent possesses local views as no agent can have a full global
view of the system and thus has incomplete capabilities to solve a problem. The data is decentralized and system displays a
decentralized behaviour, i.e., there is no controlling agent and computation is asynchronous. In MAS, agents can share
knowledge using any agreed language, within the constraints of the communication protocol of system explained later. In
MAS, there may be direct interaction or communication among agents or there are several agents that model each other's
goals and actions. shows that each agent is a part of the environment and modelled as

CLASSIFICATION OF AGENTS • Agents can be classified into different classes.• Nwana has defined a typology and classified
agents on the basis of the parameters: mobility and interaction with environment(nwana, 1996).• They maybe also be
further classified depending on the primary attributes such as autonomy, cooperation and learning ability.• The term
mobility refers to the ability of agents to move around in a given network.• Agents that posses mobility are called mobile
agents, they are able to roam around in wide-area networks, interact with foreign hosts and also perform tasks on behalf of
their owners before returning back to the originator.• We have three primary characteristics of agents are as follows:
Autonomy, Reactivity and Proactiveness

swarm? • A loosely structured collection of interacting agents •Agents: •Individuals that belong to a group (but are not
necessarily identical)•They contribute to and benefit from the group•They can recognize, communicate, and/or interact
with each other• The instinctive perception of swarms is a group of agents in motion - but that does not always• A swarm is
better understood if thought of as agents exhibiting a collective behavior
Swarm intelligence (SI): An artificial intelligence (Al) technique based on the collective behavior in decentralized, self-
organized systems •Generally made up of agents who interact with each other and the environment•No centralized control
structures•Based on group behavior found in nature

Lexical Analysis
Ci
Syntactic Analysis
Semantic Analysis
Disclosure Integration
Pragmatic Analysis
Sentence Analysis Phases
• Lexical Analysis - It involves identifying and analyzing the structure of words. Lexicon of a language means the collection of
words and phrases in a language. Lexical analysis is dividing the whole chunk of txt into paragraphs, sentences, and words.
Syntactic Analysis (Parsing) - It involves analysis of words in the sentence for grammar and arranging words in a manner that
shows the relationship among the words. The sentence such as "The school goes to boy" is rejected by English syntactic
analyzer.
• Semantic Analysis - It draws the exact meaning or the dictionary meaning from the text. The text is checked for
meaningfulness. It is done by mapping syntactic structures and objects in the task domain. The semantic analyzer disregards
sentence such as "hot ice-cream".
PPT BY: MADHAV MISHRA
53