\1. Which notation would you use to denote the 3rd layer’s activations when the input is the 7th example from the 8th minibatch?(当输入从第八个 mini-batch 的第七个的样本的时候，你会用哪种符号表示第三层的激活？)
【 】\(??^{[3]\{8\}(7)}\)
Note: [??]{??}(??)superscript means ??-th layer, ??-th minibatch, ??-th example(注意：[??]{??}(??)上标表示 第 ??层，第??小块，第??个样本)
?
\2. Which of these statements about mini-batch gradient descent do you agree with?(关于 minibatch 的说法哪个是正确的？)
【 】You should implement mini-batch gradient descent without an explicit for-loop over different mini-batches, so that the algorithm processes all mini-batches at the same time (vectorization).(在不同的 mini-batch 下，不需要显式地进行循环，就可以实现 mini-batch 梯度下降，从而使算法同时处理所有的数据（向量化）)
【 】 Training one epoch (one pass through the training set) using mini-batch gradient descent is faster than training one epoch using batch gradient descent.(使用 mini-batch 梯度下降训练的 时间（一次训练完整个训练集）比使用梯度下降训练的时间要快。)
【 】One iteration of mini-batch gradient descent (computing on a single mini-batch) is faster than one iteration of batch gradient descent.(mini-batch 梯度下降（在单个 mini-batch 上计算）的一次迭代快于梯度下降的迭代。)
【★】One iteration of mini-batch gradient descent (computing on a single mini-batch) is faster than one iteration of batch gradient descent.(mini-batch 梯度下降（在单个 mini-batch 上计 算）的一次迭代快于梯度下降的迭代。)
Note: Vectorization is not for computing several mini-batches in the same time.(注意：向量化不适用 于同时计算多个 mini-batch。)
?
\3. Why is the best mini-batch size usually not 1 and not m, but instead something inbetween?(为什么最好的 mini-batch 的大小通常不是 1 也不是 m，而是介于两者之间？)
【 】If the mini-batch size is 1, you lose the benefits of vectorization across examples in the mini-batch.(如果 mini-batch 大小为 1，则会失去 mini-batch 示例中向量化带来的的好处。)
【 】If the mini-batch size is m, you end up with batch gradient descent, which has to process the whole training set before making progress.(如果 mini-batch 的大小是 m，那么你会得到批量梯度下降，这需要在进行训练之前对整个训练集进行处理)
全对
?
\4. Suppose your learning algorithm’s cost J, plotted as a function of the number of iterations, looks like this:(如果你的模型的成本??随着迭代次数的增加，绘制出来的图如下，那么： )
【 】If you’re using mini-batch gradient descent, this looks acceptable. But if you’re using batch gradient descent, something is wrong.(如果你使用的是 mini-batch 梯度下降，这看起来 是可以接受的。但是如果你使用的是批量梯度下降，那么你的模型就有问题。)
对
Note: There will be some oscillations when you’re using mini-batch gradient descent since there could be some noisy data example in batches. However batch gradient descent always guarantees a lower ?? before reaching the optimal.(注：使用 mini-batch 梯度下降会有一些振荡，因为 mini-batch 中可能会有一些噪音数据。 然而，批量梯度下降总是保证在到达最优值之前达到较低的??。)
?
\5. Suppose the temperature in Casablanca over the first three days of January are the same:(假 设一月的前三天卡萨布兰卡的气温是一样的： )
Jan 1st: \(??_1\) = 10(一月第一天: \(??_1\) = 10)
Jan 2nd: \(??_2\) ? 10(一月第二天: \(??_2\) ? 10)
Say you use an exponentially weighted average with ?? = ??. ?? to track the temperature: \(??_??\) = ??, \(??_?? = ????_?? ? ?? + (?? ? ??)??_??\) . If \(??_??\) is the value computed after day 2 without bias correction, and \(??_??\) ?????????????????? is the value you compute with bias correction. What are these values?(假设您使用?? = ??. ??的指数加权平均来跟踪温度：\(??_?? = ??, ??_?? = ????_?? ? ?? + (?? ? ??)??_??\)。 如果????是在没有偏差修 正的情况下计算第 2 天后的值，并且\(??_??\) ??????????????????是您使用偏差修正计算的值。 这些下面的值)
【 】\(??_2 = 7.5, ??_2 ?????????????????? = 10\)
对
?
\6. Which of these is NOT a good learning rate decay scheme? Here, t is the epoch number.(下面哪一个不是比较好的学习率衰减方法？)
【 】$?? = ??^?? ? ??_0 $
dei
Note: This will explode the learning rate rather than decay it.(注：这会使得学习率出现爆炸，而没 有衰减。)
?
\7. You use an exponentially weighted average on the London temperature dataset. You use the following to track the temperature: $??_?? = ????_?? ? ?? + (?? ? ??)??_?? \(. The red line below was computed using ?? = ??. ??. What would happen to your red curve as you vary ??? (Check the two that apply)(您在伦敦温度数据集上使用指数加权平均值， 您可以使用以下公式来追踪 温度：\)??_?? = ????_?? ? ?? + (?? ? ??)??_??$。 下面的红线使用的是?? = ??. ??来计算的。 当你改变??时， 你的红色曲线会怎样变化？ )
【 】Increasing ?? will shift the red line slightly to the right.(增加??会使红线稍微向右移动。)
【 】Decreasing ?? will create more oscillation within the red line.(减少??会在红线内产生更多 的振荡。)
全对
?
\8. Consider this figure:(看一下这个图: )These plots were generated with gradient descent; with gradient descent with momentum (?? = ??. ??) and gradient descent with momentum (?? = ??.??). Which curve corresponds to which algorithm?(这些图是由梯度下降产生的; 具有动量梯 度下降（?? = ??. ??）和动量梯度下降（?? = ??. ??）。 哪条曲线对应哪种算法？ )
【 】 (1) is gradient descent. (2) is gradient descent with momentum (small ??). (3) is gradient descent with momentum (large ??)(（1）是梯度下降。 （2）是动量梯度下降（??值比较小）。 （3）是动量梯度下降（??比较大）)
对
?
\9. Suppose batch gradient descent in a deep network is taking excessively long to find a value of the parameters that achieves a small value for the cost function$ ??(??^{[??]} ,?? ^{[??]} ,… ,??^{[??]} , ??^{[??]} )\(. Which of the following techniques could help find parameter values that attain a small value for ??? (Check all that apply)(假设在一个深度学习网络中批处理梯度下降花费了太多的时间来 找到一个值的参数值，该值对于成本函数\) ??(??^{[??]} ,?? ^{[??]} ,… ,??^{[??]} , ??^{[??]} )$来说是很小的值。 以下哪些方法可以帮助找到??值较小的参数值？)
【 】 Try using Adam(尝试使用 Adam 算法)
【 】 Try better random initialization for the weights(尝试对权重进行更好的随机初始化)
【 】 Try tuning the learning rate ??(尝试调整学习率??)
【 】Try mini-batch gradient descent(尝试 mini-batch 梯度下降)
【 】Try initializing all the weights to zero(尝试把权值初始化为 0)
最后一个错误，其余全对
?
\10. Which of the following statements about Adam is False?(关于 Adam 算法，下列哪一个陈 述是错误的？)
【 】Adam should be used with batch gradient computations, not with mini-batches.(Adam 应该用于批梯度计算，而不是用于 mini-batch。)
错误
Note: Adam could be used with both.(注: Adam 可以同时使用。)
?
?
原文：https://www.cnblogs.com/phoenixash/p/12121776.html