Moe (1) 썸네일형 리스트형 [MoE 논문 리뷰] - Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity *MoE를 위한 논문 리뷰 글입니다! 궁금하신 점은 댓글로 남겨주세요! MoE paper: https://arxiv.org/abs/2101.03961 Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity In deep learning, models typically reuse the same parameters for all inputs. Mixture of Experts (MoE) defies this and instead selects different parameters for each incoming example. The result is a sparsely-activated mode.. 이전 1 다음