APPLICATIONS OF AI

The fields which are closely related with Al include Gaming, Robotics, Cognitive Science, Speech
Recognition, Natural Language Processing (NLP), Expert System and Machine Learning.
Some of the fields are:
Gaming: Al plays a crucial role in strategic games such as chess, poker, tic-tac-toe, etc., where
machines can think of a large number of possible positions based on heuristic knowledge.
Robotics: Robotics is a branch of Al, which is composed of Electrical Engineering. Mechanical
Engineering, and Computer Science for designing, construction, and application of robots.
Cognitive Science: It is the interdisciplinary study of human behaviour and intelligence, with a
focus on how information is perceived, processed, and transformed.
Speech Recognition: Speech recognition is one such technology that is empowered by Al to add
convenience to its users. This new technology has the power to convert voice messages to text.
And it also could recognize an individual based on their voice command.
Natural Language Processing (NLP): NLP is a subfield of Al which is a method of communicating
with an intelligent system using a natural language such as English and Hindi etc. Major
emphases of natural language processing include speech recognition, natural language
understanding, and natural language generation.
Expert System: An Expert System is an intelligent computer program that can perform special
and difficult tasks in some fields at the level of human experts.
INTELLIGENCE AGENTS
An agent is anything that can be viewed as perceiving its environment through sensors and
acting upon that environment through effectors
An agent in Artificial Intelligence is one that takes decisions based on rewards and punishments.
An intelligent agent is a program that can make decisions or perform a service based on its
environment, user input and experiences. These programs can be used to autonomously gather
information on a regular, programmed schedule or when prompted by the user in real time.
AGENT & ENVIRONMENT
Al can be thought of as intelligent "agents" that interact with environment.
Agent and Environment are two pillars in Artificial Intelligence. We can say that broadly agents
are the solution and environment is the problem.
In general, intelligent agents of all types (including rats, people, as well as Al programs) interact
with their environments through: Perception and Action.
1.Perception is the process of transforming something from the environment into internal
representations (memories, beliefs, etc.).
2. Action done when the agent, by doing something, changes the environment.
Agents :(1)human agent (2)robotic agent (3)software agent
**Breadth-First Search
Breadth-First searches are performed by exploring all nodes at a given depth before proceeding
to the next level. This means that all immediate children of nodes are explored before any
children's children are considered.
Advantages:(1)BFS will not get trapped explaining a blind alley which happens in depth-first
search. 2. If there is a solution, then Breadth-First Search is guaranteed to find it out.
Disadvantages: High storage requirement: exponential with tree depth
***Depth-First searches are performed by going downward into a tree as early as possible
Adv: 1Depth First Search requires less memory since only the nodes on the current path are
stored.2 If depth First Search finds a solution without examining much of the search space at all.
Dis: Incomplete: without a depth bound, may not find a solution even if one exists.
**Definition of Knowledge
The information about a domain that can be used to solve problems in that area is known as
Knowledge
TYPES: 1Declarative Knowledge: Declarative knowledge is the ability to understand something. It
includes concepts of facts, instances, objects declared as a statement. It is also called
descriptive knowledge
2 Structural Knowledge: It describes the relationship between instances and description.
3 Procedural Knowledge: It deals with the plans, procedures, strategies and rules required for a
particular system to work efficiently. It is also known as imperative knowledge
4 Meta Knowledge: It is the knowledge consisting of the higher-level data of other types of
knowledge data.
5. Heuristic Knowledge: The knowledge provided by experts of certain domains, subjects,
disciplines, and fields is known as Heuristic knowledge
***Frames:Frame is an extension to semantic network. A frame is a record like structure which
consists of a collection of attributes and its values to describe an entity in the world. Frames are
the Al data structure which divides knowledge into substructures by representing stereotypes
situations. It consists of a collection of slots and slot values. These slots may be of any type and
sizes. The frame is a type of technology which is widely used in various applications including
Natural language processing and machine visions
Advantages: 1 It is very easy to add slots for new attributes and relations.2 It is easy to include
default data and to search for missing values. 3 Frame representation is easy to understand and
visualize.
Disadvantages: 1. In frame system inference mechanism is not be easily processed.2. Inference
mechanism cannot be smoothly proceeded by frame representation.3. Frame representation has
a much generalized approach.
a much generalized approach.
** Script:A script is a structure that describes a stereotyped sequence of events in a particular
context. Also it is a set of circumstances which could be expected to follow on from one
another.A script consists of a set of slots; some information is always associated with each slot.
**Components of a Script: 1 Entry Conditions: These must be satisfied before events in the script
can occur.2 Results: Conditions that will be true after events in script occur.3 Props: Slots
representing objects involved in events.4 Roles: Persons involved in the events.5Track: Variations
on the script. Different tracks may share components of the same script.
MACHINE LEARNING: Machine learning allows a machine to learn from data, improve
performance based on experiences, and try to predict things without having to be explicitly
programmed. A machine can learn if it can improve its performance by gaining new data.
Machine learning is the process of creating or employing algorithms that learn from historical
data. The more information we supply, the better our performance will be.
Types: Supervised/Unsupervised/Reinforcement
Supervised learning, also known as supervised machine learning. It is defined as when an
algorithm learns from example data and associated target responses, which might be numeric
values or string labels such as classes or tags, in order to predict the correct response nse when
presented with new instances.
Unsupervised learning occurs when an algorithm learns from simple samples with no
accompanying response, allowing the algorithm to discover data patterns on its own. This sort of
technique restructures the data into new features that may indicate a class or a new set of
uncorrelated values. They are quite valuable in supplying people with fresh useful inputs to
supervised machine learning algorithms as well as insights into the meaning of data.
Reinforcement learning (RL) is the training of machine learning models to make a sequence of
decisions. It occurs when you present the algorithm with examples that don't have labels.
However, you can give positive or negative feedback to an example depending on the solution
the algorithm proposes
**Al Techniques are as follows:1. Search: When no more direct approach is available as well as a
framework in which any direct technique is available then search provides a way of solving
problems. A search program finds a solution for a problem by trying various sequences of
actions or operators until a solution is found. 2. Use of Knowledge: The use of knowledge
provides a way of solving complicated problems by manipulating the structures of the objects
that are concerned.3. Abstraction: Abstraction finds a way of separating important features and
notifications from the unimportant ones that would otherwise confuse any process.