The idea of a neural network is to train a non-linear function, which is usually applied to the following situations:
When many factors are determined and complex, for example, the fire of a fire building may increase, which may be determined by the wind power at that time.
, Temperature, surrounding environment, house structure, house facilities, etc. When we cannot get a correct answer based on these parameters
In this case, we can use neural networks to construct training parameters and results by selecting actual cases.
Then we can get a non-linear function.
Rules-based expert systems are usually used when we know that knowledge can be expressed in the form of IF-Else.
Knowledge to build a rule repository. When the rule repository is large enough, we can answer questions from the expert system to let us know
The fact tells it and gets the answer we want. For example, in order to determine the composition of a certain kind of ore
Color, attribute, density, and other parameters tell the expert system. The Expert System Searches the rule repository based on these conditions and then predicts the potential ore.
Type.
Machine Learning (ML): layer-based learning and re-learning Q &
Trackback: http://tb.blog.csdn.net/TrackBack.aspx? Postid = 540797