Verified70% confidenceFactExact time
The cross-entropy loss in classification tasks is essentially the negative of the log-likelihood function, and minimizing cross-entropy is equivalent to maximizing the log-likelihood of the model on the training data.
4
Sources
70%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
机器学习数学基础学习路线：四大核心板块与资源推荐
Related Claims
UnverifiedAssuming the data follows a Bernoulli or multinomial distribution, maximizing the likelihood is equivalent to minimizing the cross-entropy loss function.78% similarUnverifiedThe loss function (cross-entropy) of logistic regression is essentially negative log-likelihood.77% similarUnverified当模型对某个训练样本的预测概率接近1时，该样本对应的交叉熵损失趋近于零，模型几乎无法获得梯度更新信号77% similarUnverified交叉熵损失函数 H(p,q) = -Σp(x)log q(x) 的最小值在q=p时取到，等于真实分布的熵77% similarUnverifiedPerplexity equals the exponential of the cross-entropy loss on the test set: PPL = exp(loss), where loss=1.77 corresponds to PPL≈5.86.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/502908API
curl https://kongchang.com/api/v1/knowledge/claims/502908MCP
get_claim(id=502908)