RI: Foundations of Active Learning

RI：主动学习的基础

• 批准号: 0713540
• 负责人: Sanjoy Dasgupta
• 金额: $ 42.86万
• 依托单位: University of California-San Diego
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2007
• 资助国家: 美国
• 起止时间: 2007-08-15 至 2012-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0713540&HistoricalAwards=false
• 关键词: RI; Foundations; Active; Learning

Proposal 0713540"RI: Foundations of Active Learning"PI: Sanjoy DasguptaUniversity of California-San DiegoABSTRACTThe goal of this project is to characterize several important problems in active learning from a theoretical perspective. Active learning is a kind of machine learning, a key aspect of Robust Intelligence. A central aim of machine learning is to develop techniques that construct models of data in order to help make predictions in future situations. The past decades have seen huge advances in machine learning that uses labeled data. However, labels are often difficult to obtain. Active learning addresses situations in which the data are unlabeled, and any labels must be explicitly requested and paid for. The aim of active learning is to learn a good classifier with as few labels as possible. Despite its practical importance, active learning is a comparatively underdeveloped area in machine learning.This project will rigorously investigate the potential of intelligent querying, and develop practical, label-efficient learning algorithms. It will bring together a diversity of student talent, from theoreticians to domain experts in biology and vision applications. The resulting algorithms will be made widely available, and have the potential to increase the applicability of machine learning to the many large-scale problems in which difficulty of labeling is a critical bottleneck.

提案0713540“RI：主动学习的基础”PI：SanJoy Dasgupta加州大学圣迭戈分校这个项目的目标是从理论的角度描述主动学习中的几个重要问题。主动学习是机器学习的一种，是鲁棒智能的一个重要方面。机器学习的一个中心目标是开发构建数据模型的技术，以帮助在未来情况下做出预测。在过去的几十年里，使用标签数据的机器学习取得了巨大的进步。然而，标签往往很难获得。主动学习解决了数据没有标签的情况，任何标签都必须明确要求并支付费用。主动学习的目的是用尽可能少的标签学习一个好的分类器。尽管主动学习具有重要的实用价值，但它在机器学习中是一个相对不发达的领域。该项目将严格研究智能查询的潜力，并开发实用的、标签高效的学习算法。它将汇集各种各样的学生才华，从理论家到生物学和视觉应用领域的专家。由此产生的算法将被广泛使用，并有可能增加机器学习对许多大规模问题的适用性，其中标记的困难是一个关键的瓶颈。