Artificial Intelligence

7 min readDec 31, 2022

Photo by Possessed Photography on Unsplash

Artificial Intelligence refers to man made thinking power which is made by human beings so that machines can behave like a human being and able to make its own decisions.

💡 Father of A.I — John McCarthy

Need of A.I

A.I helps to create such software and device which can solve real world problems very easily and with accuracy such as health issues, marketing issues etc.
With the help of A.I, we can create your personal assistant for instance google assistant , Alexa, Siri
We can build such robots that can help human in survival where human can be at risk.

Goals of A.I

Replicate human intelligence
To create expert systems

Fields in A.I

Computer vision : It’s the fields of study that aims to give computers high level understanding of the world around them through digital images and video. For instance, face recognition screen lock, google lens etc.
NLP (Natural Language Processing) : this is a field of a which gives ability to machine to read, understand and derive meaning from human language. For instance google assistance ,siri
Recommendation systems : Recommendation systems are designed to suggest user something relevant things based on user’s likes and dislikes. For example Amazon, YouTube
Robotics : Robotics is an interdisciplinary sector of science and engineering dedicated to the design, construction and use of mechanical robots.

A.I Techniques

In the real world, the knowledge has some unwelcomed properties −

Its volume is huge, next to unimaginable.
It is not well-organized or well-formatted.
It keeps changing constantly.

AI Technique is a manner to organize and use the knowledge efficiently in such a way that −

It should be perceivable by the people who provide it.
It should be easily modifiable to correct errors.
It should be useful in many situations though it is incomplete or inaccurate.

Components of Intelligence

Reasoning — Judgment, making decisions, predictions
Learning — gaining knowledge
Linguistic intelligence — Comprehend speak & write
Problem solving — Working through details to find solutions
Perception — interpreting, selecting, organizing sensor information

Application of A.I

Gaming : A.I is being used to make simulated games so that we could create a virtual reality games that could save life, cost, time etc.

For instance, In defense they make simulated aircraft to teach them how to fly an aircraft this saves a lot of time, cost and life.

Vision system : Vision system are programmed a for specific task to perform and that work when something which is programmed, is occurred.

Expert system : An expert system is a computer system that imitates the decision-making ability of a human expert. Expert systems are designed to solve complex problems by reasoning through knowledge base, represented mainly as if-then rules rather than through conventional procedural code.

💡 Knowledge base : The knowledge base represents facts and rules. It consists of knowledge in a particular domain as well as rules to solve a problem, procedures and intrinsic data relevant to the domain.

History of Artificial Intelligence

1941 — The initial computer, even to run a single program. They need to do many connections and it’s used to be a complex task to do. All of this had to do because this time we didn’t have dorage concept

1943 — The first work recognized by Warren Mc Culloch and Walter Pits proposed a model of A-I neurons 1949 later on. Donald Hebb updated & modified connection strength between neurons which is called Hebbian Learning.

1950 — Alan Turing proposed a test “ computing machinery & Intelligence test to check machine ability by human intelligence.

1956 — Birth of A·I — Darth mouth conference adopted the word Artificial Intelligence by omericon scientist (John Mc Carthy).

Till now the high level languages — FORTAN, LISP and COBAL had come into existance

1966 — Joseph Wozen baum made the first chat box which name was eliza At that researchers were developing such algorithms which could. Selve mathematical problems.

1972 — The first Intelligent humanoid tobot whose name was WABOT-1 that was made in Japan. (1974–1980) Al winer ; winer means there’s shortage of funds and lack of public interest. Even government could not provide anything. And used to be postponded.

1980 — A.I came back with expert systems, they are programmed with decision making abilities. (1987–1993) — Second A.I winer: This’s because of high cost and law result at time a expert system was made CXCON).

1997 — IBM deep blue beat world chess champion (Gary Kasparov).

2002 — A.I entered in the everyone’s home in form of Roomba La Vaccum cleaner). 2006 — Further, AI entered business world, Facebook, twitter started testing AI for their businesses.

2011 — IBM watson wen Jeopardy (a quiz show) question & riddles I can solve complex. 2012 — Google launched android app (google now” It used to provide information to user as a prediction. 2014 — chatbox Eugens Geostman” won a competition in the famous. turing test. And Amazon launched Alexa an intelligent virtual assistant with a voice interface that completes shoping task. 2016 — Microsoft’s chatbox Tay goes togue on social media, making inflammatory and offensive racist comments. 2017 — Google’s AI Alpha GO beats world champion ke Jie in the complex board game of Go notable for its vast number (21) of possible position.

Turing Test

The Turing test was done in 1950 by a scientist named Alan Turing. To find whether a machine is intelligent or not. So in the Turing test. They have three room. One of rooms they have computer, another for human responder and another for human interrogator. Interrogator has to ask questions to both of them. If at the end interrogator finds there’s computer in one of rooms so it’s said that computer is not intelligent.

Problem Solving Techniques

Searching Techniques

State Space Search

A state-space is defined as a set of all possible states of a problem. A state-space representation allows for the formal definition of a problem that makes the move from the initial state to the goal state.

Problem space : Describe given problem
State : A condition or mode of the problem
State space : A State space is the set of all states reachable from the initial state
Initial state : The start state from which the program tries to solve the problem.
Set of operators : An operator is an action that can be taken within the framework of the problem that changes the current state to some other valid state in the problem.
Goal state / Solution space : The state we want the problem to be in.

Uninformed searching (Blind search) : In this searching technique, every possible states are traversed.

Breadth first search (BFS) : Breadth–first search (BFS) is an algorithm that uses FIFO(Queue) for traversing or searching tree or graph data structures. It starts at the tree root (or some arbitrary node of a graph, sometimes referred to as a ‘search key’) and explores the neighbor nodes first before moving to the next-level neighbors.
Depth first search (DFS) : Depth–first search (DFS) is an algorithm LIFO(Stack) for traversing or searching tree or graph data structures. One starts at the root (selecting some arbitrary node as the root for a graph) and explore as far as possible along each branch before backtracking.
Depth limited search : It’s similar to depth first search but with a predetermined limit that helps overcoming the problem of DFS infinite path.
Iterative deepening depth first search (IDDFS) : It’s a combination of BFS and DFS that finds out the best depth limit by increasing limit. Initially d = 0 every iteration is incremented by 1.
Bidirectional search : It is a type of search and sort activity that combines two directional approaches, so that the generator in question searches in two directions at the same time.
Uniform cost search : In this technique, the sorting is done by increasing the cost of the path to a node and the node with the least cost is expanded. And if that path doesn’t find the goal node, it backtracks
Depth first search (DFS) : Depth–first search (DFS) is an algorithm LIFO(Stack) for traversing or searching tree or graph data structures. One starts at the root (selecting some arbitrary node as the root for a graph) and explore as far as possible along each branch before backtracking.
Depth limited search : It’s similar to depth first search but with a predetermined limit that helps overcoming the problem of DFS infinite path.
Iterative deepening depth first search (IDDFS) : It’s a combination of BFS and DFS that finds out the best depth limit by increasing limit. Initially d = 0 every iteration is incremented by 1.
Bidirectional search : It is a type of search and sort activity that combines two directional approaches, so that the generator in question searches in two directions at the same time.
Uniform cost search : In this technique, the sorting is done by increasing the cost of the path to a node and the node with the least cost is expanded. And if that path doesn’t find the goal node, it backtracks.