Features of Machine Learning and Other Topics in Foundations of Computing

这个项目将有助于实现理解一个 计算机可以通过编程来学习， 增量学习算法，理论上可以增强 学习潜力。 特征被选择为类似于 人类学习。 例如，学习设备使用的结果， 一个学习插曲，以帮助在下一个学习奋进将是 考虑了 另一种强大的学习技术，对人类和机器来说， 问问题的能力 对亲属的调查 学习算法的潜力，作为他们用来摆姿势的语言 将进行提问。初步结果显示， 所用的查询语言越强大，学习就越多 设备提出问题的可能性。 查询参数 语言强度，如数量的量词和数量的 量词的变化将被严格审查。 当前的程序测试技术没有也不能确定 准确无误。 这些技术的目的是揭示 程序中的错误;但是，如果没有发现错误，则没有度量 考虑到该程序的可靠性。 因此， 如何“接近”正确的测试程序。 这个目标 研究是发展一种理论， 当一个程序通过一个给定的测试时，它有多可靠。

This project will contribute toward the goal of understanding how a computer can be programmed to learn by isolating features of incremental learning algorithms that theoretically enhance their learning potential. The features are chosen to resemble features of human learning. For example, learning devices that use the results of one learning episode to aid in the next learning endeavor will be considered. Another powerful learning technique, for both humans and machines, is the ability to ask questions. Investigations into the relative learning potential of algorithms as the language they use to pose questions will be conducted. Preliminary results indicate that the more powerful the query language used, the greater the learning potential of the device asking questions. Parameters of query language strength such as the number of quantifiers and the number of alternations of quantifiers will be vigorously examined. Current program testing techniques do not and cannot determine correctness precisely. The purpose of these techniques is to reveal errors in a program; however, if no errors are found, no measure is given as to how reliable the program is. Therefore there is no notion of how "close" to correct the tested program is. The goal of this research is to develop a theory whereby it is possible to say precisely how reliable a program is when it passes a given test.