Practice Test 1 | Google Cloud Certified Professional Data Engineer | Dumps | Mock Test
You are training a Tensorflow deep neural network model. The model should recognize different type of cars and return the brand and type of the car from the image input. While training, you decided to perform hyper-parameter tuning to optimize the model.
Which of the variables are used for hyperparameter tuning? (Choose 2)
A. Number of nodes in hidden layers
B. Number of features
C. Number of hidden layers
D. Weight values
Answer: A & C.
hyperparameters are the variables govern the training process itself. For example, part of setting up a deep neural network is deciding how many hidden layers of nodes to use between the input layer and the output layer, and how many nodes each layer should use. These variables are not directly related to the training data. They are configuration variables. Note that parameters change during a training job, while hyperparameters are usually constant during a job.
From the description, the right answers are A & C.
Answer B is incorrect: Feature numbers are set by feature engineering, not hyperparameter tuning.
Answer D is incorrect: Weight values are set when training the model.
Source(s):
Hyperparameter Tuning: https://cloud.google.com/ml-engine/docs/tensorflow/hyperparameter-tuning- overview
Comments are closed, but trackbacks and pingbacks are open.