# Full High-Dimensional Intelligible Learning In 2-D Lossless Visualization Space

arXiv: https://arxiv.org/abs/2305.19132 · HTML: https://mlsanity.com/paper/2305.19132/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 29 May 2023.

## Builds on (most cited first, 5 of 5)

- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Survey of explainable machine learning with visual and granular methods beyond quasi-explanations](https://mlsanity.com/paper/2009.10221/) (2020)
- [Full interpretable machine learning in 2D with inline coordinates](https://mlsanity.com/paper/2106.07568/) (2021)
- [Non-linear Visual Knowledge Discovery with Elliptic Paired Coordinates](https://mlsanity.com/paper/2107.04974/) (2021)
- [Visual Knowledge Discovery with General Line Coordinates](https://mlsanity.com/paper/2305.18429/) (2023)

## Abstract (arXiv)

This study explores a new methodology for machine learning classification tasks in 2-dimensional visualization space (2-D ML) using Visual knowledge Discovery in lossless General Line Coordinates. It is shown that this is a full machine learning approach that does not require processing n-dimensional data in an abstract n-dimensional space. It enables discovering n-D patterns in 2-D space without loss of n-D information using graph representations of n-D data in 2-D. Specifically, this study shows that it can be done with static and dynamic In-line Based Coordinates in different modifications, which are a category of General Line Coordinates. Based on these inline coordinates, classification and regression methods were developed. The viability of the strategy was shown by two case studies based on benchmark datasets (Wisconsin Breast Cancer and Page Block Classification datasets). The characteristics of page block classification data led to the development of an algorithm for imbalanced high-resolution data with multiple classes, which exploits the decision trees as a model design facilitator producing a model, which is more general than a decision tree. This work accelerates the ongoing consolidation of an emerging field of full 2-D machine learning and its methodology. Within this methodology the end users can discover models and justify them as self-service. Providing interpretable ML models is another benefit of this approach.