A deep learning engineer is training a convolutional neural network in TensorFlow. The training loss oscillates significantly and the model converges slowly. The engineer wants to stabilize the training process without changing the optimizer or the learning rate schedule. Which technique should be applied?

Use a different random seed for weight initialization.

Add L2 regularization to the loss function.

Increase the batch size to 256.

Add batch normalization layers between convolutional and activation layers.

A deep learning model for speech recognition is overfitting. The team wants to use dropout, but they are concerned about the impact on inference. How does dropout behave during inference?

Dropout is disabled, and all neurons are used.

Dropout is applied only to the output layer.

Dropout is replaced by batch normalization.

Dropout is still applied, but with a lower rate.

In an artificial neural network, what is the primary role of an activation function applied to a neuron's weighted sum?

To introduce non-linearity, enabling the network to learn complex patterns

To normalize the inputs to have zero mean and unit variance

To randomly drop neurons during training to prevent overfitting

To compute the gradient of the loss with respect to the weights

A company is deploying a neural network model to production. The model was trained in PyTorch, but the production environment uses TensorFlow Serving. The team needs to serve the model without retraining. Which approach is most appropriate?

Convert the PyTorch model to a Keras H5 file directly.

Use PyTorch's TorchScript to serve the model directly.

Retrain the model from scratch in TensorFlow.

Export the PyTorch model to ONNX and import it into TensorFlow.

CompTIADataX

Domain 3Objective 4

Deep Learning DY0-001 Practice Questions (Page 4)

Part of the Machine learning domain, which accounts for 24% of the DY0-001 exam. CompTIA does not publish an official question count, but from its 165-minute exam (~65–110 total, ~16–26 in this domain), expect 3–5 from this objective — we provide 24 practice questions to prepare you well beyond it. (estimate)

24questions here

5free pages

5concepts

24%of the exam

Questions 16–20

16application · medium
A deep learning engineer is training a convolutional neural network in TensorFlow. The training loss oscillates significantly and the model converges slowly. The engineer wants to stabilize the training process without changing the optimizer or the learning rate schedule. Which technique should be applied?
Select an answer first
17application · medium
A deep learning model for speech recognition is overfitting. The team wants to use dropout, but they are concerned about the impact on inference. How does dropout behave during inference?
Select an answer first
18foundation · easy
In an artificial neural network, what is the primary role of an activation function applied to a neuron's weighted sum?
Select an answer first
19foundation · easy
Which mathematical rule is the foundation of backpropagation?
Select an answer first
20expert · hard
A company is deploying a neural network model to production. The model was trained in PyTorch, but the production environment uses TensorFlow Serving. The team needs to serve the model without retraining. Which approach is most appropriate?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to DY0-001

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by CompTIA. “DY0-001” is a trademark of its owner, used for identification only.

Deep Learning DY0-001 Practice Questions (Page 4)

Questions 16–20

A deep learning model for speech recognition is overfitting. The team wants to use dropout, but they are concerned about the impact on inference. How does dropout behave during inference?

In an artificial neural network, what is the primary role of an activation function applied to a neuron's weighted sum?

Which mathematical rule is the foundation of backpropagation?

A company is deploying a neural network model to production. The model was trained in PyTorch, but the production environment uses TensorFlow Serving. The team needs to serve the model without retraining. Which approach is most appropriate?

Keep studying — Machine learning