Predicting the satisfiability of Boolean formulas by incorporating gated recurrent unit (GRU) in the Transformer framework

The Boolean satisfiability (SAT) problem exhibits different structural features in various domains. Neural network models can be used as more generalized algorithms that can be learned to solve specific problems based on different domain data than traditional rule-based approaches. How to accurately...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Wenjing Chang, Mengyu Guo, Junwei Luo
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	PeerJ Inc. 2024-08-01
Цуврал:	PeerJ Computer Science
Нөхцлүүд:	Boolean satisfiability problem Transformer Random 3-SAT Deep learning GRU Cross-attention
Онлайн хандалт:	https://peerj.com/articles/cs-2169.pdf
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!