知识卡片
平滑最大值归一产生分布
softmax将有限logit各取指数后除以所有指数之和,保持排序且总和为1。它给定候选集合上的模型分布,不自动为现实可靠置信;分母需随索引遍历z_i,不能把排版错误的同一z_k重复求和。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 用词嵌入推理
原书出处 · 1 处
- · 查看原书依据
The softmax function is often used as the activation function in the output layer of neural networks when the network’s goal is to learn classification problems. Softmax will squash the output results between 0 and 1, and the sum of all output nodes will always add up to 1. That way, the results of an output layer with a softmax function can be considered as
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第06章《用词嵌入推理》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-6.html)
- 结论依据:摘录中关于平滑最大值归一产生分布的定义、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:The softmax function is often used as the activation function in the output layer of neural networks when the network’s goal is to learn classification problems. Softmax will squash the output results between 0 and 1, and the sum of all output nodes will always add up to 1. That way, the results of an output layer with a softmax function can be considered as