Integrating Explanation-Based and Neural Approaches to Machine Learning

要被认为是智能的，机器必须能够 学习 机器学习的符号和神经方法 这两起案件都受到了深入调查。 但一直 很少有研究通过结合这些可以实现的协同效应 两种学习范式。 这项工作将开发一个混合系统 它结合了象征性的、基于抽象的 学习范式与神经反向传播算法。 在 在这个系统中，初始神经网络配置是 由解的广义解释确定， 规划任务的具体分类。 本研究 解决了选择一个好的初始神经网络的问题 配置，并克服了使用时出现的问题， 不完善的理论来建立解释。 大多数现实世界 问题永远无法精确地形式化。 然而， 通过利用近似推理的能力， 正确 基于知识的学习提供了一种方法， 有益地使用世界的因果模型，而神经网络 提供了一种方法来提炼大致正确的概念。 本研究 结合这两种学习范式， 机器学习技术的适用性，生产学习 算法是不脆弱的，可以产生概念， 其准确性通过经验来提高。

To be considered intelligent, machines must be capable of learning. Symbolic and neural approaches to machine learning both have been heavily investigated. However, there has been little research into the synergies achievable by combining these two learning paradigms. This work will develop a hybrid system that combines the symbolically-oriented explanation-based learning paradigm with the neural back-propagation algorithm. In this system, the initial neural network configuration is determined by the generalized explanation of the solution to a specific classification of planning task. This research addresses the problem of choosing a good initial neural network configuration and overcomes problems that arise when using imperfect theories to build explanations. Most real-world problems can never be formalized exactly. However, there is much to be gained by utilizing the capability to reason approximately correctly. Explanation-based learning provides a way to profitably use casual models of the world, while neural networks provide a way to refine roughly-correct concepts. This research on combining these two learning paradigms promises to broaden the applicability of machine learning techniques, producing learning algorithms that are not brittle and which can produce concepts whose accuracy improves through experience.