Unverified50% confidenceFactExact time
PReLU (Parametric ReLU) treats the slope of the negative half-axis as a learnable parameter, rather than fixing it at 0 or some constant.
1
Sources
50%
Confidence
Long-term
Relevance
10/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen positive and negative samples are imbalanced, the Precision-Recall (PR) Curve is more informative than the ROC curve; since harmful samples in guardrail testing are usually far fewer than normal samples, the PR curve is generally more appropriate.69% similarUnverifiedWhen the prediction error is assumed to follow a Gaussian distribution with zero mean and fixed variance, taking the negative logarithm of the likelihood function and expanding it yields a leading term that is exactly in the form of mean squared error.63% similarUnverifiedAdaGrad于2011年首次引入自适应学习率，对历史梯度平方累积归一化，但其分母单调递增会导致学习率趋近于零62% similarVerifiedGradient descent updates parameters through the iterative formula θ = θ - α∇J(θ), where α is the learning rate and ∇J(θ) is the vector of partial derivatives of the loss function with respect to the parameters.61% similarUnverified当正负样本比例发生变化时，ROC曲线的形状能够基本保持不变，而PR曲线通常会出现较大波动61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/981324API
curl https://kongchang.com/api/v1/knowledge/claims/981324MCP
get_claim(id=981324)