Truong quoc hiep
Truong quoc hiep

Reputation: 13

Apply a train-completed model to a new project Encog

I trained my AI and get the final model in Encog. and I know that by using NorminalizationHelper , i could get the normalization data. like in the example from "Encog quick start" below :

[ NormalizationHelper :
[ ColumnDefinition : mpg( continuous ) ; low =9.000000 , high =46.600000 ,mean
=23.514573 , sd =7.806159]
[ ColumnDefinition : c y l i n d e r s ( o r d i n a l ) ; [ 3 , 4 , 5 , 6 , 8 ] ]
[ ColumnDefinition : displa c em ent ( continuous ) ; low =68.000000 , high
=455.000000 ,mean=193.425879 , sd =104.138764]
[ ColumnDefinition : horsepower ( continuous ) ; low=?, high =?,mean=?, sd=?]
[ ColumnDefinition : weight ( continuous ) ; low =1 ,613.000000 , high
=5 ,140.000000 ,mean=2 ,970.424623 , sd =845.777234]
[ ColumnDefinition : a c c e l e r a t i o n ( continuous ) ; low =8.000000 , high
=24.800000 ,mean=15.568090 , sd =2.754222]
[ ColumnDefinition : model year ( o r d i n a l ) ; [ 7 0 , 71 , 72 , 73 , 74 , 75 , 76 ,
77 , 78 , 79 , 80 , 81 , 8 2 ] ]
[ ColumnDefinition : o r i g i n ( nominal ) ; [ 1 , 3 , 2 ] ]
]
Final model : [ BasicNetwork : Layers =3]

if I restart my AI, is there anyway to just apply this model to my AI without going through the whole re-train process. I'm still new to Encog as well as these AI stuff and I'm still digging so any idea will be appreciated.

Upvotes: 1

Views: 26

Answers (0)

Related Questions