Quantitative Analysis of Learning Algorithms

该项目致力于在统计决策理论和算法分析的方向上发展神经网络和人工智能学习的理论基础。建议的工作包括几个方面。首先，进一步扩展和应用Vapnik和Chervonenkis的统计技术。其次，一个连贯的贝叶斯方法被开发用于学习，包括Valnik-Chervonenkis理论和最近的统计物理学的学习方法。第三，开发了加权多数和其他在线学习策略，包括扩展到非平稳学习环境。最后，对无监督学习和特征发现技术进行了分析和应用。

This project is concerned with developing a theoretical foundation for learning in neural networks and artificial intelligence in the direction of statistical decision theory and analysis of algorithms. The proposed work includes several aspects. First, further extensions and applications of the statistical techniques of Vapnik and Chervonenkis are pursued. Second, a coherent Bayesian metholody is developed for learning that includes the Valnik-Chervonenkis theory and the recent statistical physics approached to learning. Third, weighted majority and other on-line learning strategies are developed, including extensions to nonstationary learning environments. Finally, analysis and application of unsupervised learning and feature discovery techniques are performed.