Question 20
Domain 3You are a junior Data Scientist and working on a deep neural network model with Tensorflow to optimize the level of customer satisfaction for after-sales services to create greater client loyalty. You are struggling with your model (learning rates, hidden layers and nodes selection) for optimizing processing and letting it converge in the fastest way. What is your problem in ML language?
Correct answer: C
Explanation
You are adjusting training settings like “learning rates, hidden layers and nodes,” which are model parameters chosen before training, so this is “hyperparameter tuning.” The source explicitly lists “Hyperparameter tuning” under training models, matching the task of finding settings that help the network converge faster and perform better.
Why each option is right or wrong
A. Cross Validation
B. Regularization
C. Hyperparameter tuning
Section 3.2 of the source explicitly includes “Hyperparameter tuning” as a training-model consideration, and the facts here name learning rate plus the number of hidden layers and nodes—classic pre-training settings that control convergence and performance. In TensorFlow, these are not learned weights but tunable configuration values chosen before or during training, so the ML term for this problem is hyperparameter tuning.
D. drift-detection management