You developed a Python module by using Keras to train a regression model. You developed two model architectures, linear regression and deep neural network (DNN), within the same module. You are…

Question

Options

• ARun one hypertuning job for 100 trials. Set num_hidden_layers as a conditional
• BRun two separate hypertuning jobs, a linear regression job for 50 trials, and a DNN job for 50 trials.
• CRun one hypertuning job with training_method as the hyperparameter for 50 trials. Select the
• DRun one hypertuning job for 100 trials. Set and as

• A
  73% (33)
• B
  13% (6)
• C
  4% (2)
• D
  9% (4)

Explanation

This approach allows you to explore both model architectures (linear regression and DNN) within a single hypertuning job while effectively managing hyperparameters. By setting as a conditional hyperparameter based on training_method, you num_hidden_layers ensure that the DNN-specific hyperparameters are only considered when the DNN architecture is selected. The learning_rate can be tuned across both architectures as a non-conditional hyperparameter. This strategy maximizes the use of the 100 trials to identify the optimal architecture and hyperparameters while minimizing training loss and maximizing model

No community discussion yet for this question.