Abstract reasoning problems pose significant challenges to artificial intelligence algorithms, demanding cognitive capabilities beyond those required for perception tasks. This study introduces the Triple-CFN approach to tackle the Bongard-Logo problem, achieving notable reasoning accuracy by implicitly reorganizing the concept space of conflicting instances. Additionally, the Triple-CFN paradigm proves effective for the RPM problem with necessary modifications, yielding competitive results. To further enhance performance on the RPM issue, we develop the Meta Triple-CFN network, which explicitly structures the problem space while maintaining interpretability on progressive patterns. The success of Meta Triple-CFN is attributed to its paradigm of modeling the conceptual space, equivalent to normalizing reasoning information. Based on this ideology, we introduce the Re-space layer, enhancing the performance of both Meta Triple-CFN and Triple-CFN. This paper aims to contribute to advancements in machine intelligence by exploring innovative network designs for addressing abstract reasoning problems, paving the way for further breakthroughs in this domain.

通过创新的网络设计来解决抽象推理问题，本研究引入了Triple-CFN方法来应对Bongard-Logo问题，通过隐式重新组织冲突实例的概念空间，实现了显著的推理准确性。此外，通过必要的修改，Triple-CFN范式在RPM问题上取得了竞争性的结果。为了进一步提高在RPM问题上的性能，我们开发了显式结构化问题空间的Meta Triple-CFN网络，同时保持逐步模式的可解释性。Meta Triple-CFN的成功归功于其对概念空间建模的范式，相当于对推理信息进行归一化处理。基于这一理念，我们引入了Re-space层，加强了Meta Triple-CFN和Triple-CFN的性能。这篇论文旨在通过探索创新的网络设计来促进机器智能的进步，为该领域的进一步突破铺平道路。

Triple-CFN：重构观念空间以增强抽象推理过程