| Package | Description |
|---|---|
| org.ai_heuristic.algo |
Some base classes for the algorithms, where they can be divided into ones that directly
compare their own dataset with other datasets, or ones that 'learn' a function first
and then use that to classify or cluster, with emphasis on information or text-based content.
|
| org.ai_heuristic.algo.classify |
Classification algorithms that categorise more than cluster.
|
| org.ai_heuristic.algo.cluster |
Clustering algorithms that try to group datasets together.
|
| org.ai_heuristic.algo.cluster.som.kohonen |
Clustering using a SOM neural network, the main cluster learning algorithms, code from http://jknnl.sourceforge.net/, but modified.
|
| org.ai_heuristic.algo.cluster.som.neighbourhood |
Clustering using a SOM neural network, for defining architecture neighbourhoods, code from http://jknnl.sourceforge.net/, but modified.
|
| org.ai_heuristic.algo.cluster.som.network |
Clustering using a SOM neural network, the neural network and node types, code from http://jknnl.sourceforge.net/, but modified.
|
| org.ai_heuristic.algo.cluster.som.topology |
Clustering using a SOM neural network, the network topologies, code from http://jknnl.sourceforge.net/, but modified.
|
| org.ai_heuristic.algo.prob |
Statistical probability algorithms, including state-based.
|
| org.ai_heuristic.algo.sort |
Some well known sorting algorithms.
|
| org.ai_heuristic.data |
Can be used for reading data files.
|
| org.ai_heuristic.def |
Some common definition interfaces that the system uses to identify types of class.
|
| org.ai_heuristic.eval |
For comparing and evaluating the different data types, with emphasis on generic classes that can be adapted to evaluate any data object.
|
| org.ai_heuristic.eval.metric |
Class model specific to this package for evaluating single data objects, or making comparisons between them.
|
| org.ai_heuristic.eval.text |
Implementations of known metrics or evaluation functions for text-specific data.
|
| org.ai_heuristic.functs |
Base classes for writing the evaluation functions or metrics.
|
| org.ai_heuristic.functs.activate |
Implementations of known activation functions that measure a firing limit threshold,
but may work with other number types, through the
org.ai_heuristic.eval.metric
data structures. |
| org.ai_heuristic.functs.learn |
Implementations of known functions that map a double value to another double value,
but may work with other number types, through the
org.ai_heuristic.eval.metric
data structures. |
| org.ai_heuristic.functs.metric |
Implementations of known metrics or evaluation functions, mostly distance or similarity,
but adapted to allow for the evaluation of any type of data object and must use the
org.ai_heuristic.eval.metric data structures. |
| org.ai_heuristic.functs.similar |
Similarity comparisons, mostly between two text-based values, but this package might
include implementations that allow for any data type, with the appropriate evaluator,
to be defined and not force the use of the
org.ai_heuristic.eval.metric data structures. |
| org.ai_heuristic.functs.test |
Test package.
|
| org.ai_heuristic.model |
For storing more complex data types, mainly text-based.
|
| org.ai_heuristic.parser |
For parsing the data structures to or from XML.
|
| org.ai_heuristic.tree |
Can be used to build tree-like structures.
|
| org.ai_heuristic.util |
Mostly pre-defined constant values, but also some utility methods.
|