---
format: "aidr-story-markdown/v1"
id: "dd1cb4a5f7daf3efde88515a36057db5a7ae96ba38fc364992b05131dfdad9c7"
canonical_url: "https://aidr.today/dd1cb4a5?lang=en"
title: "AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-02T05:00:00.000Z"
category: "Research"
topics: ["inference"]
source_urls: ["https://arxiv.org/abs/2610.40757"]
summary: "Autonomous Hebbian networks, or AutoHebb, are a class of online learning feedforward neural networks. These networks realize strong inductive biases and autonomously controlled learning. AutoHebb networks combine external feedback with internally generated activity to produce a global learning signal called a 'neuromodulator'."
---

# AutoHebb: Self\-Modifying Neural Networks that Zero\-Shot Infer and Continually Learn

> [Open the canonical story](<https://aidr.today/dd1cb4a5?lang=en>)

**Published:** 2026-11-02T05:00:00.000Z
**Category:** Research
**Topics:** inference

## Summary

Autonomous Hebbian networks, or AutoHebb, are a class of online learning feedforward neural networks\. These networks realize strong inductive biases and autonomously controlled learning\. AutoHebb networks combine external feedback with internally generated activity to produce a global learning signal called a 'neuromodulator'\.

## Sources

- [Story source](<https://arxiv.org/abs/2610.40757>)