课题基金 / 基金详情

ITR: Collaborative Research: New Directions in Predictive Learning: Rigorous Learning Machines

ITR: Collaborative Research: New Directions in Predictive Learning: Rigorous Learning Machines
ITR:协作研究:预测学习的新方向:严格的学习机器
批准号:
0325463
负责人:
Robert Schapire
金额:
$239.91万
依托单位:
依托单位国家:
美国
项目类别:
Continuing Grant
财政年份:
2003
资助国家:
美国
项目状态:
已结题
起止时间:
2003-09-01 至 2009-08-31

项目摘要

项目成果

Robert Schapire的其他基金

相似基金

相关文献

中文摘要
翻译
构建能够从实例中学习的机器是一个复杂的、跨学科的问题,涉及广泛的科学努力。学习的中心问题是理解在什么条件下,一个接受过训练以执行有限示例中的任务的系统可以将其行为概括为以前未见过的示例。这个问题与许多研究领域有关,包括认识论(如何从实验数据中得出理论?)、认知科学、统计分析、机器感知、数据挖掘、生物信息学、时间序列预测,以及许多其他领域,其中定律和知识必须从经验数据中得出。最常见的设置是监督模式识别问题:从具有已知类别的训练实例集中找到一个函数,将未知对象分类为类别。统计学习理论在过去几十年的发展为保证泛化提供了充要条件。学习算法通常分为线性和非线性两种参数化结构。支持向量机和Booking是过去几年中最成功的两种线性机器,它们都具有良好的泛化能力。对于许多应用来说,它们已经成为最先进的应用,特别是那些维度非常大的应用。另一方面,非线性机器(如多层网、隐马尔可夫模型、图形模型等)在理论上没有得到很好的刻画。这个项目的第一个目标是获得更好的泛化边界,目标是产生更好的学习算法(线性和非线性),更严格地遵循SLT框架。第二个目标将是了解非线性机器泛化的条件。第三个目标是定义和研究超越通常的归纳-演绎框架的新的推理模式,例如在线学习(其中样本被逐个处理)和转导推理(其中在训练期间可以获得测试样本),并找到实现这些新推理模式的新的学习算法(线性和非线性)。新的算法和体系结构将被应用于机器学习的一些最具挑战性和最有用的应用领域,可能包括生物信息学、机器视觉和信息检索。
英文摘要
Constructing machines capable of learning from examples is a complex, cross-disciplinary problem that spans a wide spectrum of scientific endeavor. The central issue of learning is to understand the conditions under which a system trained to perform a task from a finite set of examples can generalize its behavior to previously unseen examples. This question is relevant to many areas of research, including epistemology (how can theories be derived from experimental data?), cognitive science, statistical analysis, machine perception, data mining, bioinformatics, time series prediction, and many otherdomains where laws and knowledge must be derived from empirical data.The most common setting is the supervised pattern recognition problem: find a function that can classify unknown objects into categories from a training set of examples with known categories. The development of Statistical Learning Theory over the last few decades has provided necessary and sufficient conditions for ensuring generalization.Learning algorithms are often categorized into linearly and non-linearly parameterized architectures. Two of the most successful linear machines of the last few years, Support Vector Machines and Boosting, possess good generalization bounds. They have become the state-of-the-art for many applications, particularly those where the dimensionality is very large. On the other hand, non-linear machines (such as multilayer nets, HMMs, graphical models, and many others) are not as well characterized theoretically.The first goal of this project will be to obtain better generalization bounds with the goal of producing better learning algorithms (linear and non-linear) that follow the SLT framework more rigorously. The second goal will be to understand the conditions under which non-linear machines generalize. A third goal will be to define and study new modes of inference such as on-line learning (in which examples are processed one by one) and transductive inference (in which test examples are available during training) that go beyond the usual inductive-deductive framework, and to find new learning algorithms (linear and non-linear) that implement those new modes of inference.The new algorithms and architectures will be applied to some of the most challenging and useful application domains of machine learning, possibly including bio-informatics, machine vision and information retrieval.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
RI: Small: Boosting, Optimality and Game Theory
  • 批准号:
    1016029
  • 项目类别:
    Continuing Grant
  • 资助金额:
    $45.0万
  • 财政年份:
    2010
  • 负责人:
    Robert Schapire
  • 依托单位:
ITR: Collaborative Research: Representation and Learning in Computational Game Theory
  • 批准号:
    0325500
  • 项目类别:
    Continuing Grant
  • 资助金额:
    $42.0万
  • 财政年份:
    2003
  • 负责人:
    Robert Schapire
  • 依托单位:
海外基金