Genetic algorithms - artificial intelligence, Computer Engineering

Genetic Algorithms:

In such a scenario the evolutionary approach to "Artificial Intelligence" is one of the neatest ideas of all. Whether we have tried to mimic the functioning of the brain by neural networks this means - even however we don't know exactly how it works - so there we know that the brain does work. In fact similarly there we know that Mother Nature, during the process of evolution there has solved many problems hence for instance the problem getting animals to walk around on two feet as try getting a robot to do that - there it's very difficult. Thus seems like a good idea to mimic the processes of reproduction and survival of the fittest to try to  evolve  answers to problems but maybe in the long run reach the holy grail of computers such like program themselves by evolving programs.

Hence evolutionary approaches are simple in conception as: 

  • Here generate a population of possible answers to the problem at hand  and
  • choose the best  individuals  from the population as utilizing methods inspired through survival of the fittest. 
  • Now produce a new  generation through combining these best ones by using techniques inspired with reproduction
  • And then stop whereas the best individual of a generation is good enough as or you run out of time. 

Conceivably the first landmark in the history of the evolutionary approach to computing was John Holland's book as "Adaptation in Natural and Artificial Systems", whether he developed the idea of the genetic algorithm as searching via sampling hyperplane partitions of the space. In such a scenario it's important to keep in mind that genetic algorithms (GAs), that we look at in this lecture and other genetic programming (GP), that we look by in the next lecture that are just fancy search mechanisms such are inspired through evolution. However utilizing Tom Mitchell's definition of a machine learning system being one here that improves its performance with experience so we can see there evolutionary approaches can be classed as machine learning efforts of course. So historically moreover, it has been more common to categorize evolutionary approaches together just because of their inspiration relatively than their applications as to learning and discovery problems.

Posted Date: 1/12/2013 6:04:19 AM | Location : United States







Related Discussions:- Genetic algorithms - artificial intelligence, Assignment Help, Ask Question on Genetic algorithms - artificial intelligence, Get Answer, Expert's Help, Genetic algorithms - artificial intelligence Discussions

Write discussion on Genetic algorithms - artificial intelligence
Your posts are moderated
Related Questions
Explain Direct or Indirect Communication in Inter-process communication. Several types of message passing system in Direct or Indirect Communication are given below:

Q. Show the Bus and Memory Transfers? A digital computer has many registers and rather than connecting wires amid all registers to transfer information between them a common bu

udp connection establishment and termintion

An object model for university system Establishing relationship among various classes in the system is the primary activity. Here, we have a simple model of a University System

The free subroutine frees a block of memory lastly allocated by the malloc subroutine. Undefined results happen if the Pointer parameter is not a valid pointer. If the Pointer para

What are the major functions of IO system?  i. Interface to the CPU and memory by the system bus.  ii. Interface to one or more IO devices by tailored data link.

What happens if the both source and destination are named the same? Ans) The import operation present in MS Access does not overwrite or change any of the existing tables or obj

write a program to find the area under the curve y=f(x) between x=a and x=b,integrate y=f(x) between the limits a and b

Multiple valued logics: Multiple valued logics, where altered types of truth value such as "unknown" are may be allowed. These have some of the particular advantages of fuzzy

Convert the octal number 7401 to Binary. Ans. Octal number 7401 to Binary conversion: Every octal digit represents 3 binary digits. To change an octal number to binary number,