TrainerAlgorithm {Microsoft.VisualBasic.MachineLearning.CNN.trainers} .NET clr documentation

TrainerAlgorithm

Description

Trainers take the generated output of activations and gradients in order to modify the weights in the network to make a better prediction the next time the network runs with a data block. @author Daniel Persson (mailto.woden@gmail.com)

Declare

            
# namespace Microsoft.VisualBasic.MachineLearning.CNN.trainers
export class TrainerAlgorithm {
   batch_size: integer;
   conv_net: ConvolutionalNN;
   eps: double;
   get_output: double;
   # alpha
   learning_rate: double;
   momentum: double;
}

        

.NET clr type reference tree

  1. use by property member conv_net: ConvolutionalNN

[Package {$package} version {$version} Index]