INTRODUCTION TO AI(Artificial intelligence)

-
Well I know I have created this blog for programming language but today lets take a different subject
Artificial Intelligence.

First Question that arises in our mind that is what is artificial intelligence..??

  • Defining our answer we can say that AI is the peruses creating  the computer or Machines as Intelligent as Human being.
  • AI means Science and engineering of making intelligent machines ,especially intelligent computer programs.
  • AI is making a computer , A Computer controlled Robot.OR software think intelligently in a similar manner as humans think.

Now Thinking about the Task Domains what are the task domains of AI

The first task is the MUNDANE TASK 

MUNDANE means what..??

AI is compared especially with Human beings so what Humans do ,What Humans Think is believed to be Done from Computer ,Robot or Software. The task which Humans learn since birth are called Mundane task . They learn by perception, speaking, using language, and locomotives.
  • Vision 
  • speech
These are the Two tasks under Mundane Tasks.

Second sub task of MUNDANE TASK is Natural Language  linguistics concerned with the interactions between computers and human (natural) languages. As such, NLP(Natural Language Processing) is related to the area of human–computer interaction.

Natural language processing is a field of computer science, artificial intelligence, and computational linguistics concerned with the interactions between computers and human (natural) languages. As such, NLP is related to the area of human–computer interaction.
  • Understanding
  • Generation
  • Translation
These are the tasks under Natural language for feeding to AI in NLP.

The Third is Common Sense Reasoning.

Commonsense reasoning is one of the branches of Artificial intelligence (AI) that is concerned with simulating the human ability to make presumptions about the type and essence of ordinary situations they encounter every day. These assumptions include judgments about the physical properties, purpose, intentions and behavior of people and objects, as well as possible outcomes of their actions and interactions.

And the fourth One is ROBOT CONTROL

The most common kind of robot failure is not mechanical or electronic failure but rather failure of the software that controls the robot.

For an example its the Command who drives the Robot so programmatically we have to provide sense to it. Say for X obstacle how to Get rid of that obstacle not the same solution always applies to each and every obstacle..!!


2. FORMAL TASKS

a.Games
  • Go
  • Chess (Deep Blue)
  • Checkers
b. Mathematics
  • Geometry
  • Logic
  • Integration and Differentiation
And the 3 rd one is Expert Task under it we have
  • Engineering
  • Fault Finding
  • Manufacturing
  • Monitoring
Now coming on to what are the characteristic problems of AI..??

  1. Is the problem decomposible?
  • Means can the problem be broken into smaller problems to be solved independently?
  • As decomposible problems can be solved easily as we have seen this in Divide and conquer.
  • for example we take Ex:- ∫ x2 + 3x+sin2x cos 2x dx

    This can be done by breaking it into three smaller problems and solving each by applying specific rules. Adding the results the complete solution is obtained.

  2. Can solution steps be Ignored or Undone.?
                      
       This again Depends on the following ..!!
  • Ignorable problems :-can be solved by using simple control structure that never backtracks.
  • Recoverable problems:-can be solved using backtracking.
  • Irrecoverable problems:-this can be solved via planning.
3. Is the Universe predictable..?
  • Each time we make a move we know exactly what will happen that we call as certain outcome.
  • The opposite is we cannot know exactly what are the cards on the opponents side so that is uncertain outcome in playing Bridge.
  • for certain outcome problems planning can be used to generate sequence of operators that is guaranteed to lead a solution.
  • for uncertain outcome problem sequence of operator leads to better solution.
4.Is good solution absolute or Relative.
  • for example MARCUS was a human being in 40 AD
  • they all human being of 79 AD died in volcano erupt.
  • now we say is Marcus alive..? All path lead to the correct ans whatever you choose...!!
  • other Example is of travelling salesman problem that is try  all paths to find the shortest one.
5.Is the solution State or path..?
  • Here we can take the example of water jug problem that is the path that lead to the goal must be reported .
  • the path-solution problem can be reformatted as state-solution problem by describing state as partial path to the solution.
6.Role of Knowledge
  • for search of solution.
Moving forward,

TURING TEST
  • An AI Turing test is method of determining whether or not computer is capable of thinking like human or not.
  • According to this kind of test computer is deemed to have AI if it can mimic human responses under specific conditions.
  • If one who is checking fails to identify that response was given by human or computer than the computer is said to pass the Turing test.
  • In basic Turing test there are 3 terminals 2 terminals are operated by humans and third is operated by computer.
  • Each terminal is physically separated from the other two.
  • one human is designated as a questioner the other human  and the computer are designated as respondents.
  • The questioner Interrogates both human responder  and the computer according to specified format with certain subject area and format.
  • after the specified time the questioner tries to decide which terminal is operated by human respondent and which by computer. 

Comments

Post a Comment

Popular posts from this blog

State space search / blocks world problem by heuristic approach /TIC TAC TOE

-
A lot of AI is about SEARCH. The "state space" is the set of states of the problem we can get to by applying operators to a state of the problem to get a new state. A  state  contains  all of the information necessary to predict the effects of an action and to determine if it is a goal state. State-space searching assumes that the agent has perfect knowledge of the state space and can observe what state it is in (i.e., there is full observability); the agent has a set of actions that have known deterministic effects;some states are goal states, the agent wants to reach one of these goal states, and the agent can recognize a goal state. a solution is a sequence of actions that will get the agent from its current state to a goal state. Define the Problem as State Space Search Consider the problem of “Playing Chess” . to build a program that could play chess, we have to specify the starting position of the chess board, the rules that define legal moves. And the
Read more

Navigation in Vaadin.

-
Plain Vaadin applications do not have normal web page navigation as they usually run on a single page, as all Ajax applications do. Quite commonly, however, applications have different views between which the user should be able to navigate. The  Navigator  in Vaadin can be used for most cases of navigation. Views managed by the navigator automatically get a distinct URI fragment, which can be used to be able to bookmark the views and their states and to go back and forward in the browser history. The  Navigator  class manages a collection of  views  that implement the  View  interface. SO the class in which you are defining Navigation must implement with a  View  interface. addView() i s the method by which you can register Your View . You can add your view at any point ,Your View must have   name identifier and be added to a  View . Once registered, you can navigate to them with  navigateTo() . Navigator  manages navigation in a component container, which can be
Read more

Drag and drop items from one Grid to another

-
Following is a short example to drag and drop similar type of items from one Grid to another Grid in Vaadin 8 . package com . example . demo ; import java . util . ArrayList ; import java . util . List ; import java . util . Optional ; import com . vaadin . data . provider . ListDataProvider ; import com . vaadin . shared . ui . dnd . DropEffect ; import com . vaadin . shared . ui . dnd . EffectAllowed ; import com . vaadin . shared . ui . grid . DropMode ; import com . vaadin . ui . CustomComponent ; import com . vaadin . ui . Grid ; import com . vaadin . ui . HorizontalLayout ; import com . vaadin . ui . components . grid . GridDragSource ; import com . vaadin . ui . components . grid . GridDropTarget ; import com . vaadin . ui . renderers . ButtonRenderer ; public class DragAndDropFromGrid extends CustomComponent { /**       *      */ private static final long serialVersionUID = 1 L ; private HorizontalLayout hlytbase ;
Read more