Unverified60% confidenceFactExact time
The neural network scaling laws proposed by Kaplan et al. in 2020 indicate that model performance has a power-law relationship with data volume, parameter count, and compute, where the model's cross-entropy loss L and parameter count N satisfy L ∝ N^(-α).
2
Sources
60%
Confidence
Long-term
Relevance
9/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedNeural network scaling law research from institutions such as OpenAI has demonstrated power-law relationships between model loss and parameter count, data volume, and compute.79% similarVerifiedThe scaling laws established by Kaplan et al. in 2020 indicate that model performance follows a power-law relationship with parameter count, data volume, and compute.78% similarVerifiedThe scaling laws were systematically demonstrated in 2020 by OpenAI researcher Jared Kaplan and others, with the core finding that the cross-entropy loss of language models follows a power-law relationship with model parameter count, training data volume, and compute77% similarUnverifiedNeural ODE was proposed by Chen Tianqi et al. in a NeurIPS 2018 Best Paper, with the core idea of treating the discrete layers of a residual network as the Euler discretization of a continuous dynamical system.73% similarUnverified大模型中的参数在数学上是神经网络每条连接边上的权重数值和偏置值，训练前随机初始化，通过反向传播算法和梯度下降不断调整72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/855435API
curl https://kongchang.com/api/v1/knowledge/claims/855435MCP
get_claim(id=855435)