Skip to content
Search
Generic filters
Exact matches only

What is Artificial Intelligence?

 

what is ai?

Artificial intelligence is also called machine intelligence. Human associate with the human mind such as learning and problem solving. It is used to solve various kinds of computational problems. Artificial intelligence includes programming computers for certain trait such as:

  • Perception
  • Reasoning
  • Problem solving
  • Learning
  • Language

Perception

A percept is the input that an intelligent agent perceives at any given moment. A perception presumes sensation, where the various type of sensor who converts the simple signals into data of the system.

Reasoning

Reasoning is the process of deriving logical conclusion from the given facts. Such types of reasoning are:

  • Deducted reasoning
  • Inductive reasoning
  • Abductive reasoning
  • Analogical reasoning
  • Common sense reasoning
  • Non-monotonic reasoning

Deductive reasoning

In deductive reasoning the premises is true the conclusion must also be true. E.g.

All man are mortal. Socrates is a man

_We can deduce: Socrates is mortal.

Inductive reasoning

Premises support the conclusion but do not guarantee that it will be true.E.G.

Observation: All the crows that I have seen in my life is black

Conclusion: All crows are black

Abductive reasoning

In this reasoning the conclusion might be wrong e.g.

  • Implication: it is carries umbrella if it is raining
  • Axiom: she is carrying an umbrella
  • Conclusion: it is raining

Analogical reasoning

Analogical reasoning works between two situations, looking for similarities and differences. E.g.

Common-sense reasoning

The way to obtain common sense is by learning it or experiences it. E.g. robots

Non-monotonic reasoning

Non-monotonic reasoning is used when the facts of the case are likely to change after some time. E.g.

Rule: if the wind blows

Then: the curtains swing

Collection of information that the agent decides what to do. There are two types of problems.

  • Single state problem
  • Multi state problem

Single state problem 

When the environment is completely accessible and the agent can calculate its state after any sequence of action.

Multi state problem

When the environment is not fully accessible, the goal state may not be reachable in one action.

Problem solving agents

  • Rational agents
  • Problem solving agent

Rational agents

The agents are supposed to maximize their performance measure.

Problem solving agent

The agents which can adopt a goal.

Component of problem solving

  • Problem statement
  • Problem solution
  • Solution space
  • Traveling in the solution space

Problem statement

This is very essential component where  we give us a feel what exactly to do.it also contain the problem information and constraint over the problem.

For example:

Mouse has to get the cheese in an hour.

Problem solution

It should be known that what should be the ultimate aim of the problem.

Solution space

The set of the start state and all the intermediate state constitutes something is called a solution space.

For example;

Mouse has gone to various paths to go to the cheese.

Traveling in the solution space

The traveling inside the solution space requires something called operator. In case of the mouse example turn left, turn right, go straight are the operators which help us the problem inside the solution space.

There are a number of different forms of learning applied in artificial intelligence. The simplest is learning by trials and error.

The language use in artificial intelligence is:

  • Lisp
  • IPL
  • Prolog
  • STRIPS
  • Planner
  • Pop-11
C:UsersDuaDesktopDownloadstypes-of-artificial-intelligence copy.jpg

Narrow

It is a type of AI it is very able to perform a task with intelligence .It is trained only one specific task. For example Apple saris.

General

It can make such system which could be smarter and think like a human. System is still under research and it will take a lot of time and effort to develop such system.

Strong

In this system machine could surpass human intelligence. It can perform any task better than human with cognitive properties.

  • Reactive Machine
  • Limited Memory
  • Theory of mind
  • Self-Awareness

Reactive Machines

It does not have past memory or cannot use past information. Its only performs future action and store future information. This machine is only focus on current scenarios or current situation.

Limited memory

Its only use the past memory or can use the past information .The data can’t be store for a long time in this memory .Self-driving cars  are one of the best example of limited memory. They observe other cars speed limit and direction and nearby distance.

Theory of Mind

Theory of mind understands the human emotions and also be able to interact with human socially. This kind of machines is still not developed but researchers can do more effort to make this kind of machine.

Self-Awareness is the future of artificial intelligence.

  • It’s solving the new problems.
  • Its handle the information properly.
  • Improved interfaces.
  • Faster decisions.
  • Less errors
  • Multitasking
  • Precise
  • Intelligent  agent
  • Neural nets
  • Expert system
  • Learning
C:UsersDuaDesktopDownloads1-s2.0-S1364032115007157-gr4 copy.jpg

Machine learning is a simple concept machine . It’s a self-learning creating algorithm. It does also allow learning new things from data. Its lead knowledge.

AI performs does smart work. Its decision making .AI leads intelligence.

Deep learning is working on the human brain that process data and creates new patterns that used in decision making.

Artificial Intelligence is a mimic human behavior.

C:UsersDuaDesktopDownloadsUntitled-3 copy.jpg

The future is really unknown. The researchers seem disagree on a lot of the same issue. With the rate at which technology is improving it is logical to believe AI will continue to get more and more sophisticated.  AI permeates many job sectors in the future. It can create new career path in many fields in future.