未训练的神经网络能够展示不依赖记忆的抽象推理
Untrained neural networks can demonstrate memorization-independent abstract reasoning
AI总结：
本研究探索了无需预先训练的人工神经网络能否通过利用问题数据优化权重来实现抽象推理，在视觉推理任务上表现良好且不依赖记忆，并揭示了问题求解与知识积累的联系。
摘要：
抽象推理的本质是一个有争议的问题。现代人工神经网络（ANN）模型，如大型语言模型，在抽象推理问题的测试中表现出令人印象深刻的能力。然而，有人认为它们的成功反映的是对类似问题的某种形式的记忆（数据污染），而非通用抽象推理能力。这一担忧得到了脆弱性证据以及需要大量训练的支持。在我们的研究中，我们探讨了是否可以在没有预先训练的情况下，利用人工神经网络的工具箱实现抽象推理。具体来说，我们研究了一种人工神经网络模型，在该模型中，一个朴素网络的权重在解决问题过程中，使用问题数据本身进行优化，而非依赖任何先验知识。我们在视觉推理问题上测试了这种建模方法，发现其表现相对较好。关键在于，这一成功不依赖于对类似问题的记忆。我们进一步提出了其工作原理的解释。最后，由于问题求解是通过改变人工神经网络权重来进行的，我们探讨了问题求解与人工神经网络中知识积累之间的联系。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
