在线学习与通用模型和预测类

2006 IEEE Information Theory Workshop - ITW '06 Punta del Este Pub Date : 2006-03-13 DOI:10.1109/ITW.2006.1633819

J. Poland

{"title":"在线学习与通用模型和预测类","authors":"J. Poland","doi":"10.1109/ITW.2006.1633819","DOIUrl":null,"url":null,"abstract":"We review and relate some classical and recent results from the theory of online learning based on discrete classes of models or predictors. Among these frameworks, Bayesian methods, MDL, and prediction (or action) with expert advice are studied. We will discuss ways to work with universal base classes corresponding to sets of all programs on some fixed universal Turing machine, resulting in universal induction schemes.","PeriodicalId":293144,"journal":{"name":"2006 IEEE Information Theory Workshop - ITW '06 Punta del Este","volume":"7 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2006-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Online Learning with Universal Model and Predictor Classes\",\"authors\":\"J. Poland\",\"doi\":\"10.1109/ITW.2006.1633819\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We review and relate some classical and recent results from the theory of online learning based on discrete classes of models or predictors. Among these frameworks, Bayesian methods, MDL, and prediction (or action) with expert advice are studied. We will discuss ways to work with universal base classes corresponding to sets of all programs on some fixed universal Turing machine, resulting in universal induction schemes.\",\"PeriodicalId\":293144,\"journal\":{\"name\":\"2006 IEEE Information Theory Workshop - ITW '06 Punta del Este\",\"volume\":\"7 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2006-03-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2006 IEEE Information Theory Workshop - ITW '06 Punta del Este\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ITW.2006.1633819\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2006 IEEE Information Theory Workshop - ITW '06 Punta del Este","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ITW.2006.1633819","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

我们回顾并关联了基于离散类模型或预测器的在线学习理论的一些经典和最新结果。在这些框架中，研究了贝叶斯方法、MDL和专家建议的预测(或行动)。我们将讨论如何处理一些固定的通用图灵机上所有程序的集合所对应的通用基类，从而得到通用归纳方案。

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

Online Learning with Universal Model and Predictor Classes

We review and relate some classical and recent results from the theory of online learning based on discrete classes of models or predictors. Among these frameworks, Bayesian methods, MDL, and prediction (or action) with expert advice are studied. We will discuss ways to work with universal base classes corresponding to sets of all programs on some fixed universal Turing machine, resulting in universal induction schemes.

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

2006 IEEE Information Theory Workshop - ITW '06 Punta del Este

自引率

0.00%

发文量