按年被提到
20172017 · 1 次2026
大模型与语言模型›序列模型与注意力机制·arXiv:1711.09576 · cs.LG

Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples

Gail Weiss, Yoav Goldberg, Eran Yahav · 2017
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2017-11-28 · 最近 2020-10-07
2不同的人
2活跃月份
2讨论串
124被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We present a novel algorithm that uses exact learning and abstraction to extract a deterministic finite automaton describing the state dynamics of a given trained RNN. We do this using Angluin's L* algorithm as a learner and the trained RNN as an oracle. Our technique efficiently extracts accurate automata from trained RNNs, even when the state vectors are large and require fine differentiation.

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Cybiote · 2020-10

“> What is this sentence supposed to convey? There are examples where it is able to recognize and continue patterns in strings which if manually generated, would have required a FSM. In fact, some of the more impressive examples would require a stack of some sort so I thought I was rather underselling its capabilities in that arena. > as GPT isn't a "sta…”

AI training method exceeds GPT-3 performance with fewer parameters原评论 ↗
被提交为 story · 1 次