A Pattern-Hierarchy Classifier for Reduced Teaching

TL;DR

This paper introduces a hierarchical pattern-based classifier designed for explainable AI, combining unsupervised pattern learning with a hierarchical structure to improve classification robustness and reduce teaching effort.

Contribution

It presents a novel hierarchical classifier with nested ensemble pattern learning and new clustering algorithms, enhancing explainability and reducing the number of teaching iterations.

Findings

Ensembles are coherent, with data points belonging to the same category.

The total number of clusters can be corrected during teaching.

The approach reduces the number of teaching presentations needed.

Abstract

This paper describes a design that can be used for Explainable AI. The lower level is a nested ensemble of patterns created by self-organisation. The upper level is a hierarchical tree, where nodes are linked through individual concepts, so there is a transition from mixed ensemble masses to specific categories. Lower-level pattern ensembles are learned in an unsupervsised manner and then split into branches when it is clear that the category has changed. Links between the two levels define that the concepts are learned and missing links define that they are guessed only. This paper proposes some new clustering algorithms for producing the pattern ensembles, that are themselves an ensemble which converges through aggregations. Multiple solutions are also combined, to make the final result more robust. One measure of success is how coherent these ensembles are, which means that every data row in the cluster belongs to the same category. The total number of clusters is also important and the teaching phase can correct the ensemble estimates with respect to both of these. A teaching phase would then help the classifier to learn the true category for each input row. During this phase, any classifier can learn or infer correct classifications from some other classifier's knowledge, thereby reducing the required number of presentations. As the information is added, cross-referencing between the two structures allows it to be used more widely, where a unique structure can build up that would not be possible by either method separately.