746 お客様のコメント
質問 1：
TensorFlow is Google's first generation of proprietary machine learning systems
A. False
B. True
正解：A
質問 2：
Regarding backpropagation, the following statement is wrong?
A. Backpropagation can only be used in feedforward neural networks
B. Backpropagation can be combined with gradient descent algorithm to update network weights
C. Backpropagation passes through the activation function
D. Back propagation refers to the back propagation of errors through the network
正解：A
質問 3：
Recurrent neural networks can capture dynamic information in serialized data.
A. TRUE
B. FALSE
正解：A
質問 4：
In the gradient descent algorithm, which of the following algorithms is the most confusing algorithm for the trajectory on the loss function surface?
A. SGD
B. MBGD
C. BGD
D. MGD
正解：A
質問 5：
Linear algebra is a branch of algebra that deals with linear problems.
The linear relationship is that the relationship between exponential objects is expressed in ( ) times form?
A. 4
B. 1
C. 3
D. 2
正解：B
質問 6：
The TensorFlow framework does not support Windows systems.
A. False
B. True
正解：A
質問 7：
In a neural network, knowing the weight and deviations of each neuron is the most important step. If you know the exact weights and deviations of neurons in some way, you can approximate any function What is the best way to achieve this?
A. Assign an initial value to iteratively update weight by checking the difference between the best value and the initial
B. Search for a combmat1on of weight and deviation until the best value 1s obtained
C. The above is not correct
D. Random assignment, pray that they are correct
正解：A
TensorFlow is Google's first generation of proprietary machine learning systems
A. False
B. True
正解：A
質問 2：
Regarding backpropagation, the following statement is wrong?
A. Backpropagation can only be used in feedforward neural networks
B. Backpropagation can be combined with gradient descent algorithm to update network weights
C. Backpropagation passes through the activation function
D. Back propagation refers to the back propagation of errors through the network
正解：A
質問 3：
Recurrent neural networks can capture dynamic information in serialized data.
A. TRUE
B. FALSE
正解：A
質問 4：
In the gradient descent algorithm, which of the following algorithms is the most confusing algorithm for the trajectory on the loss function surface?
A. SGD
B. MBGD
C. BGD
D. MGD
正解：A
質問 5：
Linear algebra is a branch of algebra that deals with linear problems.
The linear relationship is that the relationship between exponential objects is expressed in ( ) times form?
A. 4
B. 1
C. 3
D. 2
正解：B
質問 6：
The TensorFlow framework does not support Windows systems.
A. False
B. True
正解：A
質問 7：
In a neural network, knowing the weight and deviations of each neuron is the most important step. If you know the exact weights and deviations of neurons in some way, you can approximate any function What is the best way to achieve this?
A. Assign an initial value to iteratively update weight by checking the difference between the best value and the initial
B. Search for a combmat1on of weight and deviation until the best value 1s obtained
C. The above is not correct
D. Random assignment, pray that they are correct
正解：A
早尾** -
この問題集を読んで基礎を理解することができました。試験には受かりそうです。Pass4Testさんの問題集はわかりやすくて重宝させてもらっています。