正则化测验

当您参加测验时，就会出现答案和解释。

1. Why would a practitioner add regularization when a model fits training-specific noise?
   • To guarantee zero training error
   • To remove the need for validation data
   • To guarantee a faster GPU kernel
   • To discourage overfitting and evaluate whether unseen-data performance improves
2. 哪种正则化技术最有可能将某些权重精确为零，从而有效地选择特征？
   • L2 正则化（权重衰减）
   • L1 正则化
   • 批量归一化
   • 提高学习率
3. Dropout 如何在训练过程中规范神经网络？
   • 它从网络中永久删除层
   • 它将平方权重添加到损失函数中
   • 它每一步都会随机关闭神经元，因此它们无法共同适应
   • 当验证损失上升时它会停止训练
4. 在正则化损失“误差+ lambda × 惩罚”中，增加 lambda 有什么作用？
   • 加强惩罚，推动模型走向更简单的解决方案
   • 削弱惩罚并允许更大的权重
   • 完全删除错误项
   • 对体重没有影响
5. 为什么早期停止可以被视为正则化的一种形式？
   • 因为它会增加损失的重量损失
   • 因为它会在模型开始在数据中拟合噪声之前停止训练
   • 因为它会随着时间的推移增加模型容量
   • 因为它随机移除神经元
6. What can happen when regularization is strengthened beyond what a task needs?
   • Both training and test accuracy must improve
   • The penalty becomes unrelated to the objective
   • Validation becomes unnecessary
   • The model can underfit useful structure even if variance decreases
7. For a regularization example with weights minus two and one, what are the unscaled L1 and sum-of-squares L2 penalties?
   • L1 is three and L2 is five
   • L1 is minus one and L2 is three
   • L1 is five and L2 is three
   • Both penalties are minus two
8. A regularized objective has prediction error two, lambda one-half, and penalty six. What is its total value?
   • 八
   • 三
   • 五
   • 一