# Correction of AI systems by linear discriminants: Probabilistic foundations

arXiv: https://arxiv.org/abs/1811.05321 · HTML: https://mlsanity.com/paper/1811.05321/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2018.

## Built on by (most cited first, 17 of 17)

- [Scikit-dimension: a Python package for intrinsic dimension estimation](https://mlsanity.com/paper/2109.02596/) (2021)
- [The Feasibility and Inevitability of Stealth Attacks](https://mlsanity.com/paper/2106.13997/) (2021)
- [High-dimensional separability for one- and few-shot learning](https://mlsanity.com/paper/2106.15416/) (2021)
- [Demystification of Few-shot and One-shot Learning](https://mlsanity.com/paper/2104.12174/) (2021)
- [Improving VAE-based Representation Learning](https://mlsanity.com/paper/2205.14539/) (2022)
- [Relative intrinsic dimensionality is intrinsic to learning](https://mlsanity.com/paper/2311.07579/) (2023)
- [How adversarial attacks can disrupt seemingly stable accurate classifiers](https://mlsanity.com/paper/2309.03665/) (2023)
- [Do stable neural networks exist for classification problems? -- A new view on stability in AI](https://mlsanity.com/paper/2401.07874/) (2024)
- [Quasi-orthogonality and intrinsic dimensions as measures of learning and generalisation](https://mlsanity.com/paper/2203.16687/) (2022)
- [Understanding the Structure of QM7b and QM9 Quantum Mechanical Datasets Using Unsupervised Learning](https://mlsanity.com/paper/2309.15130/) (2023)
- [Weakly Supervised Learners for Correction of AI Errors with Provable Performance Guarantees](https://mlsanity.com/paper/2402.00899/) (2024)
- [An Informational Space Based Semantic Analysis for Scientific Texts](https://mlsanity.com/paper/2205.15696/) (2022)
- [MyI-Net: Fully Automatic Detection and Quantification of Myocardial Infarction from Cardiovascular MRI Images](https://mlsanity.com/paper/2212.13715/) (2022)
- [Agile gesture recognition for capacitive sensing devices: adapting on-the-job](https://mlsanity.com/paper/2305.07624/) (2023)
- [Error correction in multiclass image classification of facial emotion on unbalanced samples](https://mlsanity.com/paper/2510.03337/) (2025)
- [Intrinsic Dimensionality as a Model-Free Measure of Class Imbalance](https://mlsanity.com/paper/2511.10475/) (2025)
- [Stochastic Separability of Embedding Manifolds](https://mlsanity.com/paper/2608.22874/) (2026)

## Abstract (arXiv)

Artificial Intelligence (AI) systems sometimes make errors and will make errors in the future, from time to time. These errors are usually unexpected, and can lead to dramatic consequences. Intensive development of AI and its practical applications makes the problem of errors more important. Total re-engineering of the systems can create new errors and is not always possible due to the resources involved. The important challenge is to develop fast methods to correct errors without damaging existing skills. We formulated the technical requirements to the 'ideal' correctors. Such correctors include binary classifiers, which separate the situations with high risk of errors from the situations where the AI systems work properly. Surprisingly, for essentially high-dimensional data such methods are possible: simple linear Fisher discriminant can separate the situations with errors from correctly solved tasks even for exponentially large samples. The paper presents the probabilistic basis for fast non-destructive correction of AI systems. A series of new stochastic separation theorems is proven. These theorems provide new instruments for fast non-iterative correction of errors of legacy AI systems. The new approaches become efficient in high-dimensions, for correction of high-dimensional systems in high-dimensional world (i.e. for processing of essentially high-dimensional data by large systems).