Neural Networks for Stable Disbributed Coding and Prediction

用于稳定分布式编码和预测的神经网络

• 批准号: 9401659
• 负责人: Gail Carpenter
• 金额: $ 24万
• 依托单位: Trustees of Boston 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: 1994-06-01 至 1997-11-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9401659&HistoricalAwards=false
• 关键词: Neural; Networks; Stable; Disbributed; Coding

9401659 Carpenter The proposed research will design, develop, analyze, and apply neural network architectures for stable recognition coding and prediction. One set of projects will focus on new unsupervised ART (Adaptive Resonance Theory) and supervised ARTMAP systems to support distributed recognition codes that are stable under training regimes with either fast or slow learning. Typically, the pattern of activity of a recognition code is distributed when there is little reason to select one category over another, as might occur early in a learning process. This pattern becomes more compressed as categories are more sharply defined through experience. Generalization and storage capacity of the ART neural networks will be greatly increased by the distributed coding capability. Related work will focus on the computational requirements of distributed search and on spatio-temporal recognition problems.

9401659 Carpenter拟议的研究将设计，开发，分析和应用神经网络架构，以实现稳定的识别编码和预测。 其中一组项目将专注于新的无监督ART（自适应共振理论）和有监督ARTMAP系统，以支持在快速或慢速学习的训练机制下稳定的分布式识别代码。 通常，识别码的活动模式在存在以下情况时是分布的： 在学习过程的早期，没有理由选择一个类别而不是另一个类别。 随着经验对范畴的定义更加清晰，这种模式变得更加紧凑。 ART神经网络的分布式编码能力将大大提高其泛化能力和存储容量。 相关的工作将集中在分布式搜索和时空识别问题的计算要求。