CISE Postdoctoral Program: Complexity of Learning with Applications to Natural Language

CISE博士后项目：学习的复杂性及其在自然语言中的应用

• 批准号: 9504054
• 负责人: Tomaso Poggio
• 金额: $ 4.62万
• 依托单位: Massachusetts Institute of Technology
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1995
• 资助国家: 美国
• 起止时间: 1995-03-15 至 1997-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9504054&HistoricalAwards=false
• 关键词: CISE; Postdoctoral; Program; Complexity; Learning

9504054 Poggio The research project consists of three parts. First, the investigator plans to sharpen the tools to analyze the sample complexity question -- how many examples does the learner need to generalize well? This is related to the complexity of the model the learner is using to fit the data and generalize to unseen data. Implications for model selection and data mining will be explored. Second, it is proposed to develop active algorithms which choose their own examples. This reduces the sample complexity of learning at the cost of an increased computational burden. Access to high performance computing will help greatly. Applications to function approximation, pattern classification and system identification will be explored. Finally, the tools developed earlier will be applied to the domain of natural languages. In particular, the sample complexity of learning grammar will be investigated. At the same time the evolution of human languages can be modeled as a dynamical system. This can be used as an evolutionary criterion to choose between different linguistic theories (models). ***

9504054波吉奥该研究项目由三部分组成。首先，调查人员计划磨砺工具来分析样本复杂性问题--学习者需要多少例子才能很好地概括？这与学习者用来拟合数据并将其概括为看不见的数据的模型的复杂性有关。将探讨模型选择和数据挖掘的含义。其次，提出了自主选择样例的主动算法。这降低了学习的样本复杂性，但代价是增加了计算负担。获得高性能计算将有很大帮助。将探索在函数逼近、模式分类和系统识别方面的应用。最后，前面开发的工具将应用于自然语言领域。特别是，语法学习的样本复杂性将被调查。同时，人类语言的演化也可以看作是一个动态系统。这可以作为在不同的语言理论(模式)之间进行选择的进化标准。***