The nature of abstract reasoning is a matter of debate. Modern artificial neural network (ANN) models, like large language models, demonstrate impressive success when tested on abstract reasoning problems. However, it has been argued that their success reflects some form of memorization of similar problems (data contamination) rather than a general-purpose abstract reasoning capability. This concern is supported by evidence of brittleness, and the requirement of extensive training. In our study, we explored whether abstract reasoning can be achieved using the toolbox of ANNs, without prior training. Specifically, we studied an ANN model in which the weights of a naive network are optimized during the solution of the problem, using the problem data itself, rather than any prior knowledge. We tested this modeling approach on visual reasoning problems and found that it performs relatively well. Crucially, this success does not rely on memorization of similar problems. We further suggest an explanation of how it works. Finally, as problem solving is performed by changing the ANN weights, we explored the connection between problem solving and the accumulation of knowledge in the ANNs.

翻译：抽象推理的本质一直存在争议。现代人工神经网络模型（如大型语言模型）在抽象推理问题上展现出令人瞩目的成功。然而，有观点认为这种成功反映的是对类似问题的某种记忆（数据污染），而非通用的抽象推理能力。这种担忧得到了模型脆弱性证据和大量训练需求的支持。在本研究中，我们探讨了是否能够在不进行预训练的情况下，利用人工神经网络的工具箱实现抽象推理。具体而言，我们研究了一种人工神经网络模型，其中初始网络的权重在问题求解过程中通过问题数据本身（而非任何先验知识）进行优化。我们在视觉推理问题上测试了该建模方法，发现其表现相对良好。关键的是，这种成功不依赖于对类似问题的记忆。我们进一步提出了对其工作机制的解释。最后，由于问题求解通过改变人工神经网络权重实现，我们探讨了问题求解与人工神经网络知识积累之间的联系。