Unverified50% confidenceFactExact time
For a softmax output layer, cross-entropy is a strictly convex function for single-layer models.
1
Sources
50%
Confidence
Long-term
Relevance
8/7/2026
First Seen
Sources
Related Claims
Unverified交叉熵损失函数鼓励模型将正确类别的logit推向无穷大，导致深度网络预测过于确定62% similarUnverifiedThe parameters of logistic regression are estimated by maximizing the log-likelihood function (equivalent to minimizing the cross-entropy loss).61% similarUnverifiedThe semantic entropy method is technically implemented by obtaining candidate answers through multiple samplings, using an NLI model to determine semantic equivalence for clustering, and then computing entropy over the semantic categories.60% similarUnverifiedThe binary cross-entropy loss formula is -[y·log(p) + (1-y)·log(1-p)], where y is the true label and p is the model's predicted probability for the positive class.60% similarUnverifiedEntropy can fully capture information from all moments of a probability distribution, whereas variance can only capture linear, second-order statistical relationships; mutual information can measure total dependence including nonlinear relationships, making it more general than the Pearson correlation coefficient.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/699328API
curl https://kongchang.com/api/v1/knowledge/claims/699328MCP
get_claim(id=699328)