按年被提到
20172017 · 1 次2026
数学、逻辑与理论›AI 数学与定理证明·arXiv:1705.11040 · cs.NE

End-to-End Differentiable Proving

Tim Rocktäschel, Sebastian Riedel · 2017
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2017-06-06 · 最近 2020-10-19
2不同的人
2活跃月份
2讨论串
117被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We introduce neural networks for end-to-end differentiable proving of queries to knowledge bases by operating on dense vector representations of symbols. These neural networks are constructed recursively by taking inspiration from the backward chaining algorithm as used in Prolog. Specifically, we replace symbolic unification with a differentiable computation on vector representations of symbols using a radial basis function kernel, thereby combining symbolic reasoning with learning subsymbolic vector representations. By using gradient descent, the resulting neural network can be trained to infer facts from a given incomplete knowledge base. It learns to (i) place representations of similar symbols in close proximity in a vector space, (ii) make use of such similarities to prove queries, (iii) induce logical rules, and (iv) use provided and induced logical rules for multi-hop reasoning. We demonstrate that this architecture outperforms ComplEx, a state-of-the-art neural link prediction model, on three out of four benchmark knowledge bases while at the same time inducing interpretable function-free first-order logic rules.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论maffydub · 2017-06

“I recently went to a talk at the London Machine Learning meetup (https://www.meetup.com/London-Machine-Learning-Meetup/) on "End-to-end Differentiable Proving" (https://arxiv.org/abs/1705.11040). Basically, this was about building neural networks based on propositional logic (e.g. Prolog-style statements), which was how some traditional expert systems we…”

Relational Reasoning with Neural Networks原评论 ↗
评论popinman322 · 2020-10

“IIRC these nets don't actually build a knowledge base (though I may be wrong, it's been a while). They're still functioning in lossy continuous space. This is probably fine with a low number of symbols and relations, but once you get to the level of a neural theorem prover you need to properly handle symbol binding. If I'm working with integers and inte…”

Neurosymbolic AI – Combining neural nets and symbolic AI原评论 ↗