CAREER: Connecting Human and Machine Learning through Probabilistic Models of Cognition

职业：通过概率认知模型连接人类和机器学习

• 批准号: 0845410
• 负责人: Thomas Griffiths
• 金额: $ 54.68万
• 依托单位: University of California-Berkeley
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2009
• 资助国家: 美国
• 起止时间: 2009-03-01 至 2014-02-28
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0845410&HistoricalAwards=false
• 关键词: CAREER; Connecting; Human; Machine; Learning

People are able to learn new concepts much faster than computers, often requiring only a handful of examples where a computer might require hundreds. This remarkable ability is partly the consequence of extensive experience with the world, resulting in strong prior knowledge about the kinds of objects that are likely to form categories. This research project bridges the gap between human and machine learning by developing probabilistic models of human category learning, connecting psychological data with the latest theories from computer science and statistics. These mathematical and computational models are used to explore how people learn categories so quickly, to capture the effects of prior knowledge on categorization, and to build a catalogue of human concepts that can be used to test psychological theories and to train machine learning systems. In each case, the research combines the ideas, methods, and sources of data used in psychology and computer science, using hierarchical Bayesian models and Markov chain Monte Carlo algorithms to model human cognition, laboratory experiments to test these models, and large databases as a source of statistical information that guides model predictions. This research program is integrated with an educational plan that incorporates undergraduate and graduate teaching and mentoring, development of a textbook on probabilistic models of cognition, tutorials and workshops aimed at increasing contact between the computer science and psychology communities, and outreach through talks and a website.

人们学习新概念的速度比电脑快得多，通常只需要几个例子，而电脑可能需要数百个例子。这种非凡的能力在一定程度上是对世界的广泛经验的结果，导致对可能形成类别的物体的种类有很强的先验知识。这项研究项目通过开发人类类别学习的概率模型，将心理学数据与计算机科学和统计学的最新理论联系起来，弥合了人类和机器学习之间的差距。这些数学和计算模型被用来探索人们如何如此快速地学习类别，捕捉先验知识对分类的影响，并建立可用于测试心理学理论和训练机器学习系统的人类概念目录。在每一种情况下，这项研究都结合了心理学和计算机科学中使用的思想、方法和数据来源，使用分层贝叶斯模型和马尔可夫链蒙特卡罗算法对人类认知进行建模，使用实验室实验来测试这些模型，并将大型数据库作为指导模型预测的统计信息来源。这一研究计划与一项教育计划相结合，该计划包括本科生和研究生的教学和指导，编写关于认知的概率模型的教科书，旨在增加计算机科学和心理学社区之间联系的教程和研讨会，以及通过讲座和网站进行推广。