Two models of BP neural network in the application of data prediction

There are two forms of data prediction using BP neural network:

1. Predict future data based on your own data.

For example, the value of GDP for 2013 is predicted by the value of the known GDP in 2000-2012.

Solution: Use 2000,2001,2002 value as input, 2003 as output, and so on, 2001,2002,2003 as input, 2004 as output;

...... 2009,2010,2011 as input, 2012 as output.

Prediction: The value of 2013 is predicted according to 2010,2011,2012 as input.

2. Predict an unknown property based on a known attribute.

For example: Insect 1 tentacles 1.23, length 2.45, aggression 3.88

Insect 2 tentacle 1.43, length 2.87, aggressive 3.96

Insect 3 tentacle 1.11, length 1.45, aggressive 2.88

Insect 4 Tentacles 3.23, length 4.45, aggressive.

Predict the attack of insect 4.

Solution: Based on the tentacles and the length of the insect, the attack of the insect is as output, and the input

p=[1.23,2.45;1.43,2.87;1.11,1.45;] T=[3.88;3.96;2.88]

Prediction: According to the tentacles and length of insect 4, insect 4 is predicted to be aggressive.