Training error will reduce the accuracy of the model and produce under-fitting. How to improve the model fit? (Multiple choice)
A. Add features
B. Reduce regularization parameters
C. Increase the amount of data
D. Feature Engineering
正解:A,C,D
質問 2:
Which of the following can optimization problem be classified according to the constraints? (Multiple choice)
A. equality constraints
B. Inequality constraints
C. Semi-constraint conditions
D. Unconstrained conditions
正解:A,B,D
質問 3:
Reducing the gap between the training error and the test error will result in over-fitting How to prevent over-fitting? (Multiple Choice)
A. Integration method
B. Cross validation
C. Feature Engineering
D. Increase regularization
正解:A,B,C,D
質問 4:
Which of the following options is not the- session mode used by Tensorflow?
A. Explicitly call the session to close function
B. Explicitly call the session to generate function
C. Through the Python context manager
D. Multiple POST queries
正解:D
質問 5:
TensorF1ow2.0 Can be used to check if it is tensor The methods are?
A. dtype
B. device
C. isinstance
D. is_tensor
正解:C,D
質問 6:
The model composed of machine learning algorithms cannot represent the true data distribution function on a theoretical level. Just approach it.
A. TRUE
B. FALSE
正解:A
質問 7:
TensorFlow It is one of the most popular deep learning frameworks.
A. TRUE
B. FALSE
正解:A
松村** -
またお世話になってます。10日前に購入して問題を全部覚えて行って、ようやくH13-311_V3.0合格することができました