知识卡片
序列输入输出要按任务组织
多对一可用最终状态分类,多对多可逐位置标注或编码后生成,单对多可从条件开始生成。输出对齐、停止条件和损失位置需按任务定义;采用RNN本身不决定必须只在最后一步有监督。
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
原书出处 · 1 处
- · 查看原书依据
Table 8.1 The many inputs and outputs of RNNs Type Description Applications One to many One input tensor used to generate a sequence of output tensors Generate chat messages, answer questions, describe images Many to one A sequence of input tensors gathered up into a single output tensor Classify or tag text according to its language, intent, or other characteristics Many to many A sequence
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第08章《循环网络与长短期记忆》(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-8.html)
- 结论依据:摘录中关于序列输入输出要按任务组织的定义、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:Table 8.1 The many inputs and outputs of RNNs Type Description Applications One to many One input tensor used to generate a sequence of output tensors Generate chat messages, answer questions, describe images Many to one A sequence of input tensors gathered up into a single output tensor Classify or tag text according to its language, intent, or other characteristics Many to many A sequence