知识卡片
输出映射要匹配任务表示
输出层把内部表示映射到任务要求的范围或结构,例如分类概率或图像强度。损失可以使用连续输出,实际交付还可能需要argmax、量化或格式转换。输出落在合法数值范围仅保证表示约束,不证明预测正确或已经满足任务语义。
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
- · 神经网络
原书出处 · 1 处
- · 查看原书依据
an output layer that maps a neural representation—a high-dimensional array of floating point numbers—to a desired output representation. In classification problems, the desired output is a class label, and the most common output operation is the softmax function, which we have already encountered in previous chapters. In image synthesis problems, the desired output is typically a 3D array with dimensions N × M × 3,
参考来源
- 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第12章《神经网络》(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/c012.xhtml)
- 结论依据:摘录中关于输出映射要匹配任务表示的定义、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:an output layer that maps a neural representation—a high-dimensional array of floating point numbers—to a desired output representation. In classification problems, the desired output is a class label, and the most common output operation is the softmax function, which we have already encountered in previous chapters. In image synthesis problems, the desired output is typically a 3D array with dimensions N × M × 3,