RIA: Constructive Neural Network Learning Algorithms for Pattern Classification

RIA：用于模式分类的构造性神经网络学习算法

• 批准号: 9409580
• 负责人: Vasant Honavar
• 金额: $ 11.15万
• 依托单位: Iowa State University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1994
• 资助国家: 美国
• 起止时间: 1994-07-15 至 1999-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9409580&HistoricalAwards=false
• 关键词: RIA; Constructive; Neural; Network; Learning

9409580 Honavar The primary objectives of the proposed research is a systematic exploration of a class of constructive learning algorithms for neural networks for pattern classification that can potentially: 1) Eliminate the need for ad-hoc, often inappropriate choices of network architecture; 2) Yield close to minimal networks whose complexity is commensurate with the complexity of the particular task implicitly specified by the training data; 3) Provide empirical estimates of expected-case complexity of real- world pattern classification tasks; 4) Offer natural ways to trade off some performance measures (e.g., learning time) against others (e.g., network size); 5) Provide convenient ways to incorporate domain knowledge (when available) to speed up learning.

9409580所提议的研究的主要目标是系统地探索一类用于模式分类的神经网络的建设性学习算法，其潜在地可以：1)消除对特定的、通常不适当的网络结构选择的需要；2)产生接近于其复杂性与训练数据隐含地指定的特定任务的复杂性相称的最小网络；3)提供对真实世界模式分类任务的预期情况的复杂性的经验估计；4)提供自然的方式来权衡一些性能度量(例如，学习时间)和其他性能度量(例如，网络大小)；5)提供方便的方法来整合领域知识(如果可用)以加快学习速度。