Explanation-Based Neural Network Learning

基于解释的神经网络学习

• 批准号: 9313367
• 负责人: Tom Mitchell
• 金额: $ 35.59万
• 依托单位: Carnegie-Mellon University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1993
• 资助国家: 美国
• 起止时间: 1993-12-15 至 1997-10-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9313367&HistoricalAwards=false
• 关键词: Explanation; Based; Neural; Network; Learning

This research seeks to combine the two primary paradigms for machine learning: inductive and analytical learning. Inductive methods such as instance-based and neural network learning can reliably learn simple functions from noisy data, but require vast numbers of training examples in order to scale up to very complex functions. In contrast, analytical methods such as explanation-based learning can learn complex functions from much less data, but rely upon strong prior knowledge on the part of the learner. Much current research in machine learning seeks to combine the best of both approaches, to obtain methods that learn more correct generalizations from approximate prior knowledge together with observed data. The proposed research takes a novel approach to this problem: unifying neural network learning and explanation- based learning. More specifically, this research will build on the recently developed explanation-based neural network (EBNN) learning method. Preliminary research has demonstrated experimentally that EBNN can generalize better from fewer examples than pure inductive learning if accurate domain knowledge is available, and that it degrades gracefully with the quality of the learner's prior knowledge. This research will explore more fully the space of combined neural net and explanation-based methods, focusing on issues such as scaling up to more complex learning tasks, alternative types of information that can be extracted from explanations based on neural networks, operating robustly over the entire spectrum from very strong to very weak prior knowledge, and alternative representations for the domain theory and target function. EBNN learning will be applied to two different task domains. If successful, this research could produce learning methods that scale up to more practical problems, and lead to a clearer understanding of the correspondence between symbolic and neural network approaches.

本研究旨在结合机器学习的两种主要范式：归纳学习和分析学习。基于实例和神经网络学习等归纳方法可以可靠地从噪声数据中学习简单函数，但需要大量的训练样例才能扩展到非常复杂的函数。相比之下，基于解释的学习等分析方法可以从更少的数据中学习复杂的函数，但依赖于学习者的强大先验知识。当前机器学习的许多研究都试图结合这两种方法的优点，以获得从近似先验知识和观察数据中学习更正确概括的方法。本研究采用了一种新颖的方法来解决这一问题：将神经网络学习与基于解释的学习统一起来。更具体地说，本研究将建立在最近发展的基于解释的神经网络（EBNN）学习方法的基础上。初步的研究已经通过实验证明，如果有精确的领域知识，EBNN可以从更少的例子中比纯归纳学习更好地进行泛化，并且随着学习者先验知识的质量而优雅地退化。本研究将更充分地探索结合神经网络和基于解释的方法的空间，重点关注以下问题：扩展到更复杂的学习任务，可以从基于神经网络的解释中提取的替代类型的信息，在整个范围内从非常强的先验知识到非常弱的先验知识的鲁棒性操作，以及领域理论和目标函数的替代表示。EBNN学习将应用于两个不同的任务域。如果成功的话，这项研究可能会产生更多实际问题的学习方法，并导致对符号和神经网络方法之间对应关系的更清晰理解。