Verified80% confidenceFactExact time
Cross-entropy loss originates from KL divergence in information theory and measures the degree of difference between the true probability distribution and the predicted probability distribution.
6
Sources
80%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
梯度下降与反向传播详解：神经网络学习机制从零拆解
Related Claims
UnverifiedEstimating mutual information and conditional entropy under finite samples is extremely challenging: entropy estimation for high-dimensional continuous variables has systematic bias, and commonly used k-nearest-neighbor estimators (such as the Kraskov estimator) remain unstable when the hidden state dimension is high or serial correlation is strong.76% similarUnverified香农提出的信息熵概念表明低概率事件携带更高的信息量75% similarUnverified如果交叉熵稳步下降而Dice波动剧烈，问题几乎可以确定出在Dice损失的配置上74% similarUnverifiedScaling Laws表明模型的交叉熵损失会随着计算量、数据量和参数量的增加而平滑下降，且这种下降关系可以用简单的幂律函数精确拟合73% similarUnverifiedThe model uses class-weighted cross-entropy loss, assigning each class a weight inversely proportional to its frequency to mitigate data imbalance.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/558138API
curl https://kongchang.com/api/v1/knowledge/claims/558138MCP
get_claim(id=558138)