大型世界中元学习和理性分析的挑战。

IF 16.6 1区心理学 Q1 BEHAVIORAL SCIENCES

Behavioral and Brain Sciences Pub Date : 2024-09-23 DOI:10.1017/S0140525X24000128

Margherita Calderan, Antonino Visalli

{"title":"大型世界中元学习和理性分析的挑战。","authors":"Margherita Calderan, Antonino Visalli","doi":"10.1017/S0140525X24000128","DOIUrl":null,"url":null,"abstract":"We challenge Binz et al.'s claim of meta-learned model superiority over Bayesian inference for large world problems. While comparing Bayesian priors to model-training decisions, we question meta-learning feature exclusivity. We assert no special justification for rational Bayesian solutions to large world problems, advocating exploring diverse theoretical frameworks beyond rational analysis of cognition for research advancement.","PeriodicalId":8698,"journal":{"name":"Behavioral and Brain Sciences","volume":"47 ","pages":"e148"},"PeriodicalIF":16.6000,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Challenges of meta-learning and rational analysis in large worlds.\",\"authors\":\"Margherita Calderan, Antonino Visalli\",\"doi\":\"10.1017/S0140525X24000128\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We challenge Binz et al.'s claim of meta-learned model superiority over Bayesian inference for large world problems. While comparing Bayesian priors to model-training decisions, we question meta-learning feature exclusivity. We assert no special justification for rational Bayesian solutions to large world problems, advocating exploring diverse theoretical frameworks beyond rational analysis of cognition for research advancement.\",\"PeriodicalId\":8698,\"journal\":{\"name\":\"Behavioral and Brain Sciences\",\"volume\":\"47 \",\"pages\":\"e148\"},\"PeriodicalIF\":16.6000,\"publicationDate\":\"2024-09-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Behavioral and Brain Sciences\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://doi.org/10.1017/S0140525X24000128\",\"RegionNum\":1,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"BEHAVIORAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Behavioral and Brain Sciences","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1017/S0140525X24000128","RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BEHAVIORAL SCIENCES","Score":null,"Total":0}

引用次数: 0

摘要

我们质疑 Binz 等人关于元学习模型在大型世界问题上优于贝叶斯推理的说法。在比较贝叶斯先验与模型训练决策的同时，我们质疑元学习特征的排他性。我们认为，理性贝叶斯方法解决大型世界问题并无特殊理由，我们主张探索认知理性分析之外的多种理论框架，以促进研究。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Challenges of meta-learning and rational analysis in large worlds.

We challenge Binz et al.'s claim of meta-learned model superiority over Bayesian inference for large world problems. While comparing Bayesian priors to model-training decisions, we question meta-learning feature exclusivity. We assert no special justification for rational Bayesian solutions to large world problems, advocating exploring diverse theoretical frameworks beyond rational analysis of cognition for research advancement.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Behavioral and Brain Sciences 医学-行为科学

CiteScore

1.40

自引率

1.70%

发文量

353

期刊介绍： Behavioral and Brain Sciences (BBS) is a highly respected journal that employs an innovative approach called Open Peer Commentary. This format allows for the publication of noteworthy and contentious research from various fields including psychology, neuroscience, behavioral biology, and cognitive science. Each article is accompanied by 20-40 commentaries from experts across these disciplines, as well as a response from the author themselves. This unique setup creates a captivating forum for the exchange of ideas, critical analysis, and the integration of research within the behavioral and brain sciences, spanning topics from molecular neurobiology and artificial intelligence to the philosophy of the mind.