LocalApproximator
This module chooses applies a local approximation to the input based on the input INPUT_TABLE (X) and OUTPUT_TABLE (Y). Unlike KNN_Pick, this module uses the input (X) to estimate the output.
Example XML definition
A simple example
<module
class = "LocalApproximator"
name = "LocalApproximator"
/>
Parameters
| Name | Description | Type | Default |
|---|---|---|---|
| class | The class name for the module; must be "LocalApproximator". | string | |
| name | The name of this instance of the module. | string | |
| type | The type of local approximation to be used. Linear approximation or distance weighted average. | choices: linear_approximation average distance_weighted_average | linear_approximation |
Module Connections
Inputs
| Name | Description |
|---|---|
| INPUT_TABLE | The distances of the elements (neighbors). |
| OUTPUT_TABLE | The outputs of the elements (neighbors). |
| INPUT | The input for which the output should be estimated. |
Outputs
| Name | Description |
|---|---|
| OUTPUT | The estimated output. |
Limitations
This module is work in progress and is not yet ready to be used.
Author
Alexander Kolodziej
alexander.kolodziej@gmail.com
Lund University Cognitive Science
Files
LocalApproximator.h
LocalApproximator.cc
LocalApproximator.ikc