Great endeavors have been made to study AI's ability in abstract reasoning, along with which different versions of RAVEN's progressive matrices (RPM) are proposed as benchmarks. Previous works give inkling that without sophisticated design or extra meta-data containing semantic information, neural networks may still be indecisive in making decisions regarding RPM problems, after relentless training. Evidenced by thorough experiments and ablation studies, we showcase that end-to-end neural networks embodied with felicitous inductive bias, intentionally design or serendipitously match, can solve RPM problems elegantly, without the augment of any extra meta-data or preferences of any specific backbone. Our work also reveals that multi-viewpoint with multi-evaluation is a key learning strategy for successful reasoning. Finally, potential explanations for the failure of connectionist models in generalization are provided. We hope that these results will serve as inspections of AI's ability beyond perception and toward abstract reasoning. Source code can be found in https://github.com/QinglaiWeiCASIA/RavenSolver.

翻译：为探究AI的抽象推理能力，学界已做出大量努力，并由此提出了不同版本的RAVEN渐进矩阵（RPM）作为基准测试。先前研究表明，即便不采用复杂设计或包含语义信息的额外元数据，经过持续训练的神经网络在解决RPM问题时仍可能难以做出明确判断。通过详尽的实验与消融研究，我们证明：具备恰当归纳偏置的端到端神经网络——无论这种偏置是刻意设计的还是偶然匹配的——无需任何额外元数据或特定主干网络的偏好，即可优雅地解决RPM问题。我们的工作还揭示，多视角结合多评估是成功推理的关键学习策略。最后，本文为联结主义模型在泛化任务中的失败提供了潜在解释。希望这些结果能成为审视AI超越感知迈向抽象推理能力的检验依据。源代码见 https://github.com/QinglaiWeiCASIA/RavenSolver。