Trainer
The Trainer module reads one or two data sets and use them to train a learning module. The data can be used either sequentially or be read out in random order. Half or all of the data in the input set can be used for validation. Alternatively, the validation comes from a separate source.
Example XML definition
Trainer
<module
class = "Trainer"
name = "Trainer"
/>
Parameters
| Name | Description | Type | Default |
|---|---|---|---|
| class | The class name for the module; must be "Trainer". | string | |
| name | The name of this instance of the module. | string | |
| order | Order in which to present data | choices: random sequential | |
| crossvalidation | Which data should be used for crossvalidation? | choices: none all even odd input |
Module Connections
Inputs
| Name | Description |
|---|---|
| TRAINING_DATA_X | Training data set X-values |
| TRAINING_DATA_Y | Training data set Y-values |
| TESTING_DATA_X | Testing data set X-values |
| TESTING_DATA_Y | Testing data set Y-values |
| TEST_Y | Output generated by the learning module |
Outputs
| Name | Description |
|---|---|
| TRAIN_X | Data to send to the training input of the learning module |
| TRAIN_Y | Data to send as target output of the learning module |
| TEST_X | Data to send to the input of the learning module |
| ERROR | The current validation error |
Author
Christian Balkenius
christian.balkenius@lucs.lu.se
Lund University Cognitive Science
Files
Trainer.h
Trainer.cc
Trainer.ikc