Connectionist Learning Algorithms for Temporal Processing and Multi-Scale Search

用于时间处理和多尺度搜索的联结学习算法

• 批准号: 8921275
• 负责人: Ronald Williams
• 金额: $ 19.77万
• 依托单位: Northeastern University
• 依托单位国家: 美国
• 项目类别: Continuing grant
• 财政年份: 1990
• 资助国家: 美国
• 起止时间: 1990-08-01 至 1994-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=8921275&HistoricalAwards=false
• 关键词: Connectionist; Learning; Algorithms; Temporal; Processing

This grant will support Dr. Williams' theoretical and experimental work in two important areas of artificial neural computation: recursive networks for processing time-varying signals, and multiscale networks for exploiting information at multiple resolutions. Recursive networks will be important for control and signal-processing problems with feedback delays of unknown duration. Multiscale architectures and learning strategies are needed for large-scale problems of practical importance, including those with complex spatial and temporal components. Proposed target applications are in speech recognition and adaptive sensorimotor control.

这笔赠款将支持威廉姆斯博士在人工神经计算的两个重要领域的理论和实验工作：用于处理时变信号的递归网络，以及用于以多分辨率利用信息的多尺度网络。对于具有未知持续时间的反馈延迟的控制和信号处理问题，递归网络将是重要的。对于具有实际重要性的大规模问题，包括那些具有复杂空间和时间成分的问题，需要多尺度体系结构和学习策略。提出的目标应用是语音识别和自适应感觉运动控制。