Post Doctoral: Probabilistic Models for Hierarchical Neural Networks

博士后：分层神经网络的概率模型

• 批准号: 9404932
• 负责人: Michael Jordan
• 金额: $ 4.35万
• 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: 1994
• 资助国家: 美国
• 起止时间: 1994-09-01 至 1996-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9404932&HistoricalAwards=false
• 关键词: Post; Doctoral; Probabilistic; Models; Hierarchical

9404932 Jordan The Associateship in Experimental Science will support a program of interdisciplinary research at the Massachusetts Institute of Technology. The proposed research will focus on probabilistic models for hierarchical neural networks. Two specific architectures will be studied in detail: hierarchical mixtures-of-experts (HME) and Boltzmann trees. HME networks that model mixtures of more complicated probabilistic processes, such as hidden Markov chains and optimal observers will be developed. The expectation-maximization (EM) principle from statistics will be utilized to develop learning algorithms for these architectures. The behavior of these EM algorithms will be analyzed by exploiting the relationship of EM to mean-field theories from statistical physics. Boltzmann machines are a general class of probabilistic model for constraint satisfaction whose development has been hindered by the lack of an efficient learning algorithm. Boltzmann machines with tree-like architectures have simplifying features that make them faster and more efficient. Further work on Boltzmann trees will lead to more powerful algorithms for supervised and unsupervised learning. Various parallels between Boltzmann trees and belief networks for probabilistic reasoning will be explained. ***

9404932 Jordan 实验科学联营奖学金将支持麻省理工学院的跨学科研究计划。 拟议的研究将集中于分层神经网络的概率模型。 将详细研究两种特定的架构：分层专家混合（HME）和玻尔兹曼树。 将开发对更复杂的概率过程的混合进行建模的 HME 网络，例如隐马尔可夫链和最优观察者。 统计学中的期望最大化（EM）原理将用于开发这些架构的学习算法。 将通过利用电磁与统计物理学中的平均场理论的关系来分析这些电磁算法的行为。 玻尔兹曼机是一类用于约束满足的概率模型，其发展因缺乏有效的学习算法而受到阻碍。 具有树状架构的玻尔兹曼机具有简化的功能，使其更快、更高效。 对玻尔兹曼树的进一步研究将带来更强大的监督和无监督学习算法。 将解释玻尔兹曼树和概率推理的信念网络之间的各种相似之处。 ***