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:
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.