weixin_40833196的博客

文章目录Intro两大学派的争论先验与后验、似然 Intro 学MLE时遇到这么一句话 A nice feature of this view is that we can now also interpret the regularization term R(W) in the full loss function as coming from a Gaussian prior over t...

文章目录IntroFormulationProbabilistic interpretationMLEInformation theory viewKullback-Leibler divergencePractical issues: Numeric stabilityPossibly confusing naming conventions Intro Softmax classifier 是...

Intro Regularization is an additional part in loss function or optimiazation loss, which prevent the loss function from doing too well on training data. Formulation indeed, the regularation prefer a...