引导式测验 · 中等 等级
损失函数测验
测试预测目标、平方误差和绝对误差、类交叉熵、可用的训练导数、损失单位和数值误差平均值。
问题 1 的 8
对于预测任务,其选择的损失函数如何量化相对于训练目标的表现?
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。
- 对于预测任务,其选择的损失函数如何量化相对于训练目标的表现?
- A specified prediction-error objective
- Only runtime speed
- 仅网络层数
- Every application benefit automatically
- 哪种损失函数最常用于分类任务?
- 均方误差
- 平均绝对误差
- 交叉熵损失
- 仅铰链距离
- 与均方误差相比,为什么您会选择平均绝对误差?
- 纠正错误以给予更多惩罚
- 它对异常值更加稳健,因为它不会平方误差
- 不能用于回归
- 它忽略了真正的标签
- 为什么基于梯度的训练需要可用的损失导数或合适的替代品?
- So a loss number can be printed
- So all learning methods become identical
- So the dataset no longer needs targets
- So backpropagation and optimization can obtain an update signal
- 当分配给目标类的概率变得非常小时,独热类交叉熵会如何变化?
- Its loss must become zero
- It rewards the prediction increasingly
- Its loss becomes large
- It becomes identical to accuracy
- 为什么准确率通常不直接用作训练损失?
- 它是不可微分的,因此它没有给出有用的梯度
- 计算起来太容易了
- 它只适用于回归
- 无论如何,它总是等于损失
- For illustrative regression residuals one and three, what are mean squared error and mean absolute error?
- MSE is two and MAE is five
- Both are four
- MSE is ten and MAE is four
- MSE is five and MAE is two
- Using a base-two logarithm, what one-hot cross-entropy loss corresponds to target-class probability one-quarter?
- One-quarter bit
- Two bits
- Four bits
- Zero bits