KDI: Learning, Adaptation and Layered Intelligent Systems

KDI：学习、适应和分层智能系统

• 批准号: 9873451
• 负责人: Sanjoy Mitter
• 金额: $ 120万
• 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: 1998
• 资助国家: 美国
• 起止时间: 1998-10-01 至 2002-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9873451&HistoricalAwards=false
• 关键词: KDI; Learning; Adaptation; Layered; Intelligent

9873451MitterOur approach to building intelligent systems is based on the theoretical ideas of Bayesian statistical signal analysis and control-theoretic motion guidance. These theories have achieved major successes in many widely used systems. However, it has remained a challenge to create systems that integrate the analysis of low-level concrete sensor data and motor control with the use of high-level, more abstract representations of perception and action. The investigators on our team propose to attack this central issue with a variety of approaches. We believe that a very promising tool is the systematic study of hierarchical compositional data structures, in which larger scale more abstract objects are built up in stages from small-scale concrete objects. This compositional approach applies to making decisions as well as to perception: subtasks may be composed into larger tasks and reasoned with as units. Doing reasoning in such hybrid systems, it is essential that ambiguity and multiple alternatives be maintained as long as possible. For example, this means not choosing between inconsistent high-level interpretations of a signal until larger scale context is available; or replacing a local 'greedy algorithm' decision by a dynamic programming-style list of optimal conditional decisions. We discuss the role of learning in such hierarchical layered systems. Understanding, the interaction between information and control in such layered systems is a critical research issueWe plan to concentrate our research on the following aspects of layered intelligent systems:(i) the role of the compositional and hierarchical approach in language and speech recognition; (ii) hierarchical decision making in layered systems; (iii) learning of hierarchical concepts; and (iv) interaction information and control in distributed systems. We emphasize that these topics are highly inter-related. ***

我们构建智能系统的方法是基于贝叶斯统计信号分析和控制论运动制导的理论思想。这些理论已经在许多广泛使用的系统中取得了重大成功。然而，创建将低级别具体传感器数据的分析和电机控制与使用更高级别的、更抽象的感知和行动表示相结合的系统仍然是一个挑战。我们团队的调查人员建议用各种方法来解决这个中心问题。我们认为，一个非常有前途的工具是系统地研究层次组成数据结构，其中更大规模的更抽象的对象是从小规模的具体对象分阶段建立起来的。这种组合方法既适用于决策，也适用于感知：子任务可以组合成更大的任务，并作为单位进行推理。在这样的混合系统中进行推理时，尽可能长时间地保持歧义和多个备选方案是至关重要的。例如，这意味着在更大规模的上下文可用之前，不要在信号的不一致的高级解释之间进行选择；或者用动态编程风格的最优条件决策列表来取代局部的“贪婪算法”决策。我们讨论了学习在这种分层系统中的作用。我们计划将我们的研究集中在以下几个方面：(I)组成和分层方法在语言和语音识别中的作用；(Ii)分层系统中的分层决策；(Iii)分层概念的学习；以及(Iv)分布式系统中的交互信息和控制。我们强调，这些议题高度相关。***