---
id: 20261103-T0-08
title: "AutoHebb：能零样本推理并持续学习的自修改神经网络"
title_en: "AutoHebb: Self-Modifying Neural Networks That Do Zero-Shot Inference and Keep Learning"
url: https://ai.daily.yangsir.net/daily/20261103-T0-08
issue_date: 2026-11-03
publish_date: 2026-11-02T05:00:00.000Z
source_name: "arXiv cs.LG (ML)"
source_url: https://arxiv.org/abs/2610.40757
---

# AutoHebb：能零样本推理并持续学习的自修改神经网络

论文提出AutoHebb，一类自修改神经网络，目标是同时实现零样本推理（ZI）和持续学习（CL）这两种人类和动物具备的认知能力。研究指出，现有建模这两种能力的工作存在明显局限，AutoHebb通过让网络自身修改连接结构来应对新环境下的泛化与知识保留问题。如果该方法在更大规模上成立，将指向一类无需重新训练就能适应新任务、且不遗忘旧知识的模型。

## English Version

**AutoHebb: Self-Modifying Neural Networks That Do Zero-Shot Inference and Keep Learning**

The paper introduces AutoHebb, a class of self-modifying neural networks aimed at both zero-shot inference and continual learning, two cognitive abilities humans and animals share. The authors note that existing efforts to model these abilities have serious limitations; AutoHebb lets the network modify its own connections to generalize in novel settings while retaining prior knowledge. If the approach holds at larger scale, it points toward models that adapt to new tasks without retraining and without forgetting old ones.

---

**来源**：[arXiv cs.LG (ML)](https://arxiv.org/abs/2610.40757)

**详情页**：https://ai.daily.yangsir.net/daily/20261103-T0-08

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*