Unverified50% confidenceFactExact time
The surrogate model embeds physical laws into neural network training in the form of a loss function, to maintain physical consistency of predictions when data is scarce.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
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% similarUnverifiedA loss function is the objective function optimized when training a neural network; it defines the mathematical standard for "good."76% similarUnverifiedThe 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).74% 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74% similarUnverifiedDiffusion models and flow matching absorb the sampling cost once during training by training a neural network, requiring only a forward pass at inference time.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114474API
curl https://kongchang.com/api/v1/knowledge/claims/1114474MCP
get_claim(id=1114474)