知识卡片
模型对比应固定任务与评价
MLP和CNN可用于相同数字标签任务,但其输入组织与结构偏好不同。书中两种架构设计只是候选;必须在一致划分和指标下训练评价,不能从CNN利用空间结构直接宣称已优于MLP。
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
- · 深度学习模型
原书出处 · 1 处
- · 查看原书依据
Example 8.2: Let us revisit Example 8.1 but this time using CNN as the classification architecture. As we discuss this example, you will notice that we are solving the same classification task as in Example 8.1 (i.e., designing a classifier to predict the handwritten digit presented in the input image), but we are approaching the problem slightly differently by choosing a different architecture and corresponding
参考来源
- 位置:《Machine Learning Fundamentals: Concepts, Models, and Applications》第08章《深度学习模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Machine Learning Fundamentals: Concepts, Models, and Applications/_epub-src/OEBPS/xhtml/21_chapter08.xhtml)
- 结论依据:摘录中关于模型对比应固定任务与评价的定义、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:Example 8.2: Let us revisit Example 8.1 but this time using CNN as the classification architecture. As we discuss this example, you will notice that we are solving the same classification task as in Example 8.1 (i.e., designing a classifier to predict the handwritten digit presented in the input image), but we are approaching the problem slightly differently by choosing a different architecture and corresponding