For many reasoning-heavy tasks involving raw inputs, it is challenging to
design an appropriate end-to-end learning pipeline. Neuro-Symbolic Learning,
divide the process into sub-symbolic perception and symbolic reasoning, trying
to utilise data-driven machine learning and knowledge-driven reasoning
simultaneously. However, they suffer from the exponential computational
complexity within the interface between these two components, where the
sub-symbolic learning model lacks direct supervision, and the symbolic model
lacks accurate input facts. Hence, most of them assume the existence of a
strong symbolic knowledge base and only learn the perception model while
avoiding a crucial problem: where does the knowledge come from? In this paper,
we present Abductive Meta-Interpretive Learning ($Meta_{Abd}$) that unites
abduction and induction to learn neural networks and induce logic theories
jointly from raw data. Experimental results demonstrate that $Meta_{Abd}$ not
only outperforms the compared systems in predictive accuracy and data
efficiency but also induces logic programs that can be re-used as background
knowledge in subsequent learning tasks. To the best of our knowledge,
$Meta_{Abd}$ is the first system that can jointly learn neural networks from
scratch and induce recursive first-order logic theories with predicate
invention.

本篇论文介绍了一种称为 Abductive Meta-Interpretive Learning ($Meta_{Abd}$) 的方法，该方法结合了知识推理和归纳学习技术，从数据中共同学习神经网络和逻辑理论，并证明了该方法在预测准确性和数据效率方面的优越性，以及可以在后续学习任务中重复使用的背景知识。

从原始数据中归纳出的演绎知识

Abductive Knowledge Induction From Raw Data

A large part of the use of knowledge base systems is the interpretation of
the output by the end-users and the interaction with these users. Even during
the development process visualisations can be a great help to the developer. We
created IDPD3 as a library to visualise models of logic theories. IDPD3 is a
new version of $ID^{P}_{Draw}$ and adds support for visualised interactive
simulations.

介绍了 IDPD3 库，作为一种 visualisations 工具， 用于知识库系统中逻辑理论和交互式模拟的可视化和解释。