---
title: "Curriculum unlearning in humans and neural networks"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.04565v1"
permalink: "https://feed.astralor.com/items/itm_78136123eaa5fff37c5de86a"
published: "2026-11-03T09:27:50.000Z"
score: 56
channel: "ai"
tags: ["Curriculum","During","However","Here","Simple-to-complex"]
---

# Curriculum unlearning in humans and neural networks

## 速览

During learning, humans often benefit from curricula that teach simple rules before exceptions. However, we lack a computational explanation for this phenomenon. Here, using a canonical behavioural task and modelling wi…

## 关键点

- During learning, humans often benefit from curricula that teach simple rules before exceptions.
- However, we lack a computational explanation for this phenomenon.
- Here, using a canonical behavioural task and modelling with neural networks, we develop and test a theory for why simple-to-complex curricula succeed.

## 全文

During learning, humans often benefit from curricula that teach simple rules before exceptions. However, we lack a computational explanation for this phenomenon. Here, using a canonical behavioural task and modelling with neural networks, we develop and test a theory for why simple-to-complex curricula succeed. We show that during learning, both humans and neural networks show simplicity biases, a tendency to learn simple rules that are underfit to the data. In neural networks this bias is accompanied by compression of neural representations. Simple-to-complex curricula help both types of learners overcome this compression, developing representations (and policy) with appropriate dimensionality for the task. We test and confirm a further prediction from this theory: learners that have been pre-exposed to simple tasks and with more compressed initial representations benefit more from curricula. These findings suggest that curricula help with ``unlearning'' of simple rules.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_78136123eaa5fff37c5de86a