Franziska Bröker, Lori L Holt, Brett D Roads, Peter Dayan, Bradley C Love
{"title":"揭开无监督学习的神秘面纱:它的帮助与伤害","authors":"Franziska Bröker, Lori L Holt, Brett D Roads, Peter Dayan, Bradley C Love","doi":"10.1016/j.tics.2024.09.005","DOIUrl":null,"url":null,"abstract":"<p><p>Humans and machines rarely have access to explicit external feedback or supervision, yet manage to learn. Most modern machine learning systems succeed because they benefit from unsupervised data. Humans are also expected to benefit and yet, mysteriously, empirical results are mixed. Does unsupervised learning help humans or not? Here, we argue that the mixed results are not conflicting answers to this question, but reflect that humans self-reinforce their predictions in the absence of supervision, which can help or hurt depending on whether predictions and task align. We use this framework to synthesize empirical results across various domains to clarify when unsupervised learning will help or hurt. This provides new insights into the fundamentals of learning with implications for instruction and lifelong learning.</p>","PeriodicalId":49417,"journal":{"name":"Trends in Cognitive Sciences","volume":" ","pages":"974-986"},"PeriodicalIF":16.7000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Demystifying unsupervised learning: how it helps and hurts.\",\"authors\":\"Franziska Bröker, Lori L Holt, Brett D Roads, Peter Dayan, Bradley C Love\",\"doi\":\"10.1016/j.tics.2024.09.005\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Humans and machines rarely have access to explicit external feedback or supervision, yet manage to learn. Most modern machine learning systems succeed because they benefit from unsupervised data. Humans are also expected to benefit and yet, mysteriously, empirical results are mixed. Does unsupervised learning help humans or not? Here, we argue that the mixed results are not conflicting answers to this question, but reflect that humans self-reinforce their predictions in the absence of supervision, which can help or hurt depending on whether predictions and task align. We use this framework to synthesize empirical results across various domains to clarify when unsupervised learning will help or hurt. This provides new insights into the fundamentals of learning with implications for instruction and lifelong learning.</p>\",\"PeriodicalId\":49417,\"journal\":{\"name\":\"Trends in Cognitive Sciences\",\"volume\":\" \",\"pages\":\"974-986\"},\"PeriodicalIF\":16.7000,\"publicationDate\":\"2024-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Trends in Cognitive Sciences\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://doi.org/10.1016/j.tics.2024.09.005\",\"RegionNum\":1,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/9/30 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"BEHAVIORAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Trends in Cognitive Sciences","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1016/j.tics.2024.09.005","RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/9/30 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"BEHAVIORAL SCIENCES","Score":null,"Total":0}
Demystifying unsupervised learning: how it helps and hurts.
Humans and machines rarely have access to explicit external feedback or supervision, yet manage to learn. Most modern machine learning systems succeed because they benefit from unsupervised data. Humans are also expected to benefit and yet, mysteriously, empirical results are mixed. Does unsupervised learning help humans or not? Here, we argue that the mixed results are not conflicting answers to this question, but reflect that humans self-reinforce their predictions in the absence of supervision, which can help or hurt depending on whether predictions and task align. We use this framework to synthesize empirical results across various domains to clarify when unsupervised learning will help or hurt. This provides new insights into the fundamentals of learning with implications for instruction and lifelong learning.
期刊介绍:
Essential reading for those working directly in the cognitive sciences or in related specialist areas, Trends in Cognitive Sciences provides an instant overview of current thinking for scientists, students and teachers who want to keep up with the latest developments in the cognitive sciences. The journal brings together research in psychology, artificial intelligence, linguistics, philosophy, computer science and neuroscience. Trends in Cognitive Sciences provides a platform for the interaction of these disciplines and the evolution of cognitive science as an independent field of study.