Unverified50% confidenceFactExact time
Kaplan等人2020年的研究表明模型参数量、训练数据量、训练计算量三者与性能之间存在可预测的幂律关系
1
Sources
50%
Confidence
Long-term
Relevance
7/21/2026
First Seen
Sources
Related Claims
UnverifiedThe training-time scaling law was proposed by Kaplan et al. in 2020, holding that model capability is primarily determined by parameter count, training data volume, and training compute.82% similarVerifiedThe Scaling Law proposed by OpenAI reveals that model performance improves in a predictable power-law fashion as the number of parameters, training data volume, and compute increase.74% similarUnverified根据Chinchilla定律及其后续研究，模型性能与训练计算量之间存在幂律关系73% similarUnverified批次归一化在训练模式使用当前批次统计量，在推理模式使用训练过程中累积的移动平均值71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/576257API
curl https://kongchang.com/api/v1/knowledge/claims/576257MCP
get_claim(id=576257)