引导式测验 · 中等 等级
少样本学习测验
通过支持/查询角色、原型计算、符号和提示排序,比较上下文演示和基于度量的小样本学习。
问题 1 的 8
In an N-way K-shot classification episode, what does K count?
预览每个问题8 问题
当您参加测验时,就会出现答案和解释。
- In an N-way K-shot classification episode, what does K count?
- The number of classes
- Labeled support examples per class
- All parameters in the model
- The number of optimization epochs
- 当大型语言模型根据提示进行上下文中的几次学习时,其权重会发生什么?
- 它们在提示示例上略有微调
- 它们被重置为特定于任务的检查点
- 它们保持不变;这些例子只是预测的条件
- 它们与示例嵌入进行平均
- 零次提示和少次提示之间的主要区别是什么?
- 零样本没有提供有效的例子;几次拍摄提供了一些
- 零样本使用比少样本更小的模型
- 零样本总是比少样本表现更好
- 零样本需要标记训练数据,而少样本则不需要
- How can prior learning contribute to a few-shot task?
- It guarantees every arbitrary demonstration yields the intended rule
- It requires copying each example as every final answer
- It necessarily retrains all network weights during prompting
- It can supply useful learned patterns or representations for interpreting the small support set
- 其中描述了像原型网络这样基于度量的小样本方法?
- 它将示例标签写入数据库以供查找
- 它生成合成示例,直到有数千个
- 它将新样本与每个类的几个样本的平均嵌入进行比较,并选择最接近的样本
- 它使用来自人类反馈的强化学习
- 实践者发现,只需在几次提示中重新排列示例即可改变准确性。这说明了什么?
- GPU 中的硬件错误
- 少数镜头的性能可能对示例顺序和格式很敏感
- 模型与测试集过度拟合
- 零射击是不可能的
- A class has embedded support points (0,0) and (2,0). What arithmetic-mean prototype does the stated prototypical method form?
- (2,0)
- (0,2)
- (2,2)
- (1,0)
- Which distinction defines support and query roles in the original prototypical-network episode?
- Support labels construct class prototypes; separate query items evaluate classification
- Query labels must be copied into every support prototype
- Support items contain no labels by definition
- The two sets must always contain exactly the same sampled examples