Polynomial-Time Algorithms for Accurate Approximation and Estimation of Functions by Neural Nets

用于神经网络函数精确逼近和估计的多项式时间算法

• 批准号: 9410760
• 负责人: Andrew Barron
• 金额: $ 13.39万
• 依托单位: Yale 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: 1994-09-15 至 1997-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9410760&HistoricalAwards=false
• 关键词: Polynomial; Time; Algorithms; Accurate; Approximation

9410760 Barron The goal of the project is the development and proof of computationally feasible algorithms for training artificial neural networks that provide accurate approximation, estimation, and classification for general classes of functions in high dimensions. The analysis involves Markov chain convergence theory, based on a decomposition of the neural net likelihood function as a mixture of log-concave functions, and an information-theoretic analysis of Bayes estimators of neural nets. Practical computer implementation will also be investigated.

9410760巴伦 该项目的目标是开发和证明计算上可行的算法，用于训练人工神经网络，为高维函数的一般类提供准确的近似，估计和分类。 分析涉及马尔可夫链收敛理论，基于神经网络的似然函数的对数凹函数的混合物的分解，和贝叶斯估计的神经网络的信息理论分析。 实际的计算机实现也将进行调查。