nuget
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)
TrainerAlgorithm
01 Syntax
Microsoft.VisualBasic.MachineLearning.CNN.trainers.TrainerAlgorithm
02 Methods
| Name | Overloads | Summary |
|---|---|---|
| SetKernel | 1 | |
| train | 1 | |
| update | 1 | |
| initTrainData | 1 |
03 Properties
| Name | Overloads | Summary |
|---|---|---|
| learning_rate | 1 | alpha |
| eps | 1 | |
| momentum | 1 | |
| batch_size | 1 | |
| conv_net | 1 | |
| get_output | 1 |
04 Fields
| Name | Overloads | Summary |
|---|---|---|
| k | 1 | iteration counter |
05 Members
learning_rate
alpha
k
iteration counter
eps
momentum
batch_size
conv_net
get_output
SetKernel(ConvolutionalNN)
update(
Int32, Int32, Double, Double())initTrainData(BackPropResult)