Verified90% confidenceFactExact time
The theoretical roots of the Mixture of Experts model can be traced back to the mixture of experts system proposed by Jacobs et al. in 1991.
8
Sources
90%
Confidence
Long-term
Relevance
7/6/2026
First Seen
Sources
284B大模型跑进MacBook：DeepSeek本地推理的真实突破与门槛
bilibili声译看世界7/3/2026
Related Claims
VerifiedThe Mixture of Experts (MoE) architecture can be traced back to the neural network ensemble theory proposed by Jacobs et al. in 1991.82% similarVerifiedMoE架构的核心思想源自1991年Jacobs等人提出的混合专家系统79% similarUnverifiedThe Mixture of Experts architecture can be traced back to the theoretical framework proposed by Jacobs et al. in 1991, but it was not truly introduced into the field of large-scale language models until Google's Switch Transformer paper in 2017.73% similarUnverifiedMoE理论根源可追溯到1991年Jacobs等人的论文《Adaptive Mixtures of Local Experts》70% similarVerifiedThe Mixture of Experts (MOE) architecture was first proposed by Hinton et al. in 1991.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/113941API
curl https://kongchang.com/api/v1/knowledge/claims/113941MCP
get_claim(id=113941)