arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.07968cs.LGcs.AIcs.CL
收藏

基于非符号神经网络的关系推理与泛化

Relational reasoning and generalization using non-symbolic neural networks

Stanford University(斯坦福大学)

Atticus Geiger, Alexandra Carstensen, Michael C. Frank, Christopher Potts

摘要:

平等(身份)的概念是简单和普遍存在的,使其成为一个关键的案例研究更广泛的问题表示支持抽象的关系推理。以前的研究表明,神经网络不是人类关系推理的合适模型,因为它们不能表示数学上的同一性,即最基本的平等形式。我们重新讨论这个问题。在我们的实验中,我们使用任意表示和在单独的任务上预先训练的表示来评估平等的样本外泛化,以使它们具有结构。我们发现神经网络能够学习(1)基本等式(数学恒等式),(2)仅使用正训练实例的序列等式问题(学习ABA模式序列),以及(3)仅使用基本等式训练实例的复杂分层等式问题(“零射击”泛化)。在后两种情况下,我们的模型执行先前工作中提出的任务,以划分人类独特的符号能力。这些结果表明,符号推理的基本方面可以从数据驱动的非符号学习过程中出现。

英文摘要:

The notion of equality (identity) is simple and ubiquitous, making it a key case study for broader questions about the representations supporting abstract relational reasoning. Previous work suggested that neural networks were not suitable models of human relational reasoning because they could not represent mathematically identity, the most basic form of equality. We revisit this question. In our experiments, we assess out-of-sample generalization of equality using both arbitrary representations and representations that have been pretrained on separate tasks to imbue them with structure. We find neural networks are able to learn (1) basic equality (mathematical identity), (2) sequential equality problems (learning ABA-patterned sequences) with only positive training instances, and (3) a complex, hierarchical equality problem with only basic equality training instances ("zero-shot'" generalization). In the two latter cases, our models perform tasks proposed in previous work to demarcate human-unique symbolic abilities. These results suggest that essential aspects of symbolic reasoning can emerge from data-driven, non-symbolic learning processes.

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。

↑