Multilayer Perceptron for Prediction of 2006 World Cup Football Game

Table 4

Procedures of determining the parameters for BP learning rule.

To determine parameters	Fixed conditions	Variable conditions	Observation items
Momentum coefficient 𝛽	(1) Hidden nodes=6; (2) MSE=0.01; (3) 𝜂=0.1	(1) 𝛽=0.5,0.6,0.7,0.8,0.9; (2) Testing times=40	Average convergent iterations and standard deviation of convergent iterations
Learning rate 𝜂	(1) Hidden nodes=6; (2) MSE=0.01; (3) 𝛽=0.8	(1) 𝜂=0.1,0.3,0.5,0.7,0.9; (2) Testing times=40	Average convergent iterations