# Brain experiments imply adaptation mechanisms which outperform common AI learning algorithms

arXiv: https://arxiv.org/abs/2005.04106 · HTML: https://mlsanity.com/paper/2005.04106/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [Supervised Hebbian Learning](https://mlsanity.com/paper/2203.01304/) (2022)
- [Power-law Scaling to Assist with Key Challenges in Artificial Intelligence](https://mlsanity.com/paper/2211.08430/) (2022)
- [Efficient shallow learning as an alternative to deep learning](https://mlsanity.com/paper/2211.11106/) (2022)
- [Unified CNNs and transformers underlying learning mechanism reveals multi-head attention modus vivendi](https://mlsanity.com/paper/2501.12900/) (2025)
- [Learning on tree architectures outperforms a convolutional feedforward network](https://mlsanity.com/paper/2211.11378/) (2022)
- [Enhancing the accuracies by performing pooling decisions adjacent to the output layer](https://mlsanity.com/paper/2303.05800/) (2023)
- [ElegansNet: a brief scientific report and initial experiments](https://mlsanity.com/paper/2304.13538/) (2023)

## Abstract (arXiv)

Attempting to imitate the brain functionalities, researchers have bridged between neuroscience and artificial intelligence for decades; however, experimental neuroscience has not directly advanced the field of machine learning. Here, using neuronal cultures, we demonstrate that increased training frequency accelerates the neuronal adaptation processes. This mechanism was implemented on artificial neural networks, where a local learning step-size increases for coherent consecutive learning steps and tested on a simple dataset of handwritten digits, MNIST. Based on our online learning results with a few handwriting examples, success rates for brain-inspired algorithms substantially outperform the commonly used machine learning algorithms. We speculate this emerging bridge from slow brain function to machine learning will promote ultrafast decision making under limited examples, which is the reality in many aspects of human activity, robotic control, and network optimization.