# The unreasonable effectiveness of small neural ensembles in high-dimensional brain

arXiv: https://arxiv.org/abs/1809.07656 · HTML: https://mlsanity.com/paper/1809.07656/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2018.

## Built on by (most cited first, 10 of 10)

- [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)
- [Stealth edits to large language models](https://mlsanity.com/paper/2406.12670/) (2024)
- [Including STDP to eligibility propagation in multi-layer recurrent spiking neural networks](https://mlsanity.com/paper/2201.07602/) (2022)
- [Quasi-orthogonality and intrinsic dimensions as measures of learning and generalisation](https://mlsanity.com/paper/2203.16687/) (2022)
- [A Mathematical Framework for the Problem of Security for Cognition in Neurotechnology](https://mlsanity.com/paper/2403.07945/) (2024)
- [Networks with Finite VC Dimension: Pro and Contra](https://mlsanity.com/paper/2502.02679/) (2025)
- [Theoretical Lower Bounds on the Robustness of Deep ReLU Networks](https://mlsanity.com/paper/2602.18674/) (2026)

## Abstract (arXiv)

Despite the widely-spread consensus on the brain complexity, sprouts of the single neuron revolution emerged in neuroscience in the 1970s. They brought many unexpected discoveries, including grandmother or concept cells and sparse coding of information in the brain. In machine learning for a long time, the famous curse of dimensionality seemed to be an unsolvable problem. Nevertheless, the idea of the blessing of dimensionality becomes gradually more and more popular. Ensembles of non-interacting or weakly interacting simple units prove to be an effective tool for solving essentially multidimensional problems. This approach is especially useful for one-shot (non-iterative) correction of errors in large legacy artificial intelligence systems. These simplicity revolutions in the era of complexity have deep fundamental reasons grounded in geometry of multidimensional data spaces. To explore and understand these reasons we revisit the background ideas of statistical physics. In the course of the 20th century they were developed into the concentration of measure theory. New stochastic separation theorems reveal the fine structure of the data clouds. We review and analyse biological, physical, and mathematical problems at the core of the fundamental question: how can high-dimensional brain organise reliable and fast learning in high-dimensional world of data by simple tools? Two critical applications are reviewed to exemplify the approach: one-shot correction of errors in intellectual systems and emergence of static and associative memories in ensembles of single neurons.