论文标题
从原始数据中学习答案集程序的神经符号学习
Neuro-Symbolic Learning of Answer Set Programs from Raw Data
论文作者
论文摘要
人工智能的最终目标之一是协助人类进行复杂的决策。实现这一目标的有希望的方向是神经符号AI，该AI旨在将符号技术的解释性与深度学习从原始数据中学习的能力相结合。但是，当前大多数方法都需要手动设计的符号知识，并且在考虑端到端培训的地方，这种方法要么仅限于学习确定的程序，要么仅限于培训二进制神经网络。在本文中，我们介绍了神经符号归纳学习者（NSIL），这种方法训练了一种通用神经网络以从原始数据中提取潜在概念，而学习符号知识将潜在概念映射到目标标签。我们方法的新颖性是一种基于神经和符号成分的训练表现的象征性知识学习的方法。我们在不同复杂性的三个问题域（包括NP完整问题）上评估NSIL。我们的结果表明，NSIL学习表现力知识，解决计算复杂的问题，并在准确性和数据效率方面实现最先进的性能。代码和技术附录：https：//github.com/dancunnington/nsil
One of the ultimate goals of Artificial Intelligence is to assist humans in complex decision making. A promising direction for achieving this goal is Neuro-Symbolic AI, which aims to combine the interpretability of symbolic techniques with the ability of deep learning to learn from raw data. However, most current approaches require manually engineered symbolic knowledge, and where end-to-end training is considered, such approaches are either restricted to learning definite programs, or are restricted to training binary neural networks. In this paper, we introduce Neuro-Symbolic Inductive Learner (NSIL), an approach that trains a general neural network to extract latent concepts from raw data, whilst learning symbolic knowledge that maps latent concepts to target labels. The novelty of our approach is a method for biasing the learning of symbolic knowledge, based on the in-training performance of both neural and symbolic components. We evaluate NSIL on three problem domains of different complexity, including an NP-complete problem. Our results demonstrate that NSIL learns expressive knowledge, solves computationally complex problems, and achieves state-of-the-art performance in terms of accuracy and data efficiency. Code and technical appendix: https://github.com/DanCunnington/NSIL
