知识卡片

普通读书笔记卡 · 8992.c · 生成模型:GPT-6

编码与生成可共享下界目标

理解等级:中级

把ELBO同时对编码器ψ和生成模型θ优化,使一方改善近似推断、另一方改善潜变量解释数据的方式。固定θ时可从ψ目标中丢掉log pθ(x),但更新θ时它不再是常数。所有“忽略常数”都必须先明确对哪个参数求导。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      This way our learning problem for both θ and ψ share the same objective (which also saves computation) and can be stated simply as: (33.32) The VAE objective, J, is often called the Evidence Lower Bound or ELBO, because it is a lower-bound on the data log-likelihood (i.e. Jp, which equals log pθ(x)). log pθ(x) is sometimes referred to as the evidence for x. Using

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第33章《生成建模与表示学习》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c033.xhtml) - 结论依据:摘录中关于编码与生成可共享下界目标的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:This way our learning problem for both θ and ψ share the same objective (which also saves computation) and can be stated simply as: (33.32) The VAE objective, J, is often called the Evidence Lower Bound or ELBO, because it is a lower-bound on the data log-likelihood (i.e. Jp, which equals log pθ(x)). log pθ(x) is sometimes referred to as the evidence for x. Using