# MIT researchers show neural networks can build own learning rules

Digest AI · Research · published 2026-10-13T21:00:00Z

Canonical: https://digestai.news/story/mit-researchers-show-neural-networks-can-build-own-learning-rules

## Summary

Scientists at MIT’s McGovern Institute and K. Lisa Yang Integrative Computational Neuroscience Center published a paper in PNAS on Oct. 9, arguing that artificial neural networks should be judged by their ability to self-organize rather than by performance alone. The team, led by researcher Liao and including Liu Ziyin and Yulu Gan, developed a computational network that starts with randomly connected units. Instead of relying on complex, hand-designed architectures, this network uses simple rules, such as "neurons that fire together wire together," to reshape its own connections and learning machinery.

The researchers demonstrated that this self-organizing network can learn to recognize patterns and classify images, achieving performance levels similar to networks trained using standard back-propagation. However, the team notes that back-propagation is unlikely to be how the brain actually learns. By focusing on self-organization, the model offers a more biologically plausible framework for understanding how biological brains organize themselves without an external architect.

Liao and colleagues suggest that understanding these self-organizing rules could aid in developing brain-computer interfaces and neuroprosthetics, which require knowledge of neuron-neuron interactions. While the primary goal is neuroscience, the team believes these insights could eventually lead to machine learning systems that perform better or in more human-like ways.

## Key points

- MIT researchers published a paper in PNAS on Oct. 9 about self-organizing neural networks.
- The network uses simple rules to reshape connections, mimicking biological learning processes.
- The self-organizing model performs similarly to networks using standard back-propagation algorithms.

## Why it matters

This research bridges AI and neuroscience by proposing a biologically plausible mechanism for learning. It could improve brain-computer interfaces and lead to AI systems that learn more efficiently or human-like, moving beyond standard back-propagation.

## Sources

1. [How artificial neural networks build their own learning machinery](https://news.mit.edu/2026/how-artificial-neural-networks-build-their-own-learning-machinery-1013) (MIT News on AI, 2026-10-13, primary source)

## Cite

Digest AI, "MIT researchers show neural networks can build own learning rules", 13 October 2026, https://digestai.news/story/mit-researchers-show-neural-networks-can-build-own-learning-rules

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/mit-researchers-show-neural-networks-can-build-own-learning-rules.json