论文标题
学习结构化的声明规则集 - 深入离散学习的挑战
Learning Structured Declarative Rule Sets -- A Challenge for Deep Discrete Learning
论文作者
论文摘要
可以说，深层神经网络成功的关键原因是它们能够自主形成输入特征的非线性组合的能力，这些功能可用于网络的后续层。在归纳规则学习中，对这种能力的类似物是学习结构化规则基础，其中将输入结合在一起以学习新的辅助概念，然后可以通过后续规则将其用作输入。然而，对具有这种能力的规则学习算法的研究仍处于起步阶段，这是 - 我们认为 - 在该领域取得实质性进步的关键障碍之一。在该立场论文中，我们想引起人们对这个未解决的问题的关注，特别关注谓语发明和多标签规则学习
Arguably the key reason for the success of deep neural networks is their ability to autonomously form non-linear combinations of the input features, which can be used in subsequent layers of the network. The analogon to this capability in inductive rule learning is to learn a structured rule base, where the inputs are combined to learn new auxiliary concepts, which can then be used as inputs by subsequent rules. Yet, research on rule learning algorithms that have such capabilities is still in their infancy, which is - we would argue - one of the key impediments to substantial progress in this field. In this position paper, we want to draw attention to this unsolved problem, with a particular focus on previous work in predicate invention and multi-label rule learning
