cs.AI updates on arXiv.org 07月30日 12:11
What Does it Mean for a Neural Network to Learn a "World Model"?
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出一套评估神经网络学习世界模型的精确标准,旨在为实验研究提供共同语言,基于线性探测文献,并确保模型非数据或任务的简单结果。

arXiv:2507.21513v1 Announce Type: new Abstract: We propose a set of precise criteria for saying a neural net learns and uses a "world model." The goal is to give an operational meaning to terms that are often used informally, in order to provide a common language for experimental investigation. We focus specifically on the idea of representing a latent "state space" of the world, leaving modeling the effect of actions to future work. Our definition is based on ideas from the linear probing literature, and formalizes the notion of a computation that factors through a representation of the data generation process. An essential addition to the definition is a set of conditions to check that such a "world model" is not a trivial consequence of the neural net's data or task.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

神经网络 世界模型 学习标准 线性探测 数据生成
相关文章