GIAC Machine Learning Engineer
Domain 3Objective 3
Neural Networks GMLE Practice Questions (Page 1)
Part of the Advanced Machine Learning and Neural Networks domain, which makes up ~30% of our current practice bank. GIAC (SANS) does not publish an official question count, but from its 180-minute exam (~70–120 total, ~21–36 in this domain), expect 7–12 from this objective — we provide 39 practice questions to prepare you well beyond it. (estimate)
39questions here
8free pages
9concepts
Questions 1–5
- 1
Which optimization algorithm maintains a per-parameter learning rate by using the moving average of squared gradients?
Select an answer first - 2
A neural network has an input layer with 3 features, a hidden layer with 2 neurons using ReLU, and an output layer with 1 neuron using sigmoid. The weights and biases are initialized. During forward propagation, one of the hidden neurons receives a weighted sum of -2.0. What is the output of that hidden neuron?
Select an answer first - 3
A machine learning engineer is training a deep neural network for image classification. The loss curve shows high variance and the training is unstable, with the loss oscillating significantly. The engineer suspects the learning rate is too high. Which of the following adjustments would most directly address this issue?
Select an answer first - 4
A neural network has one hidden layer with 3 neurons using ReLU activation and an output layer with 1 neuron using linear activation. The input is a 2-dimensional vector. What is the shape of the weight matrix for the hidden layer?
Select an answer first - 5
Why is the sigmoid activation function less preferred in deep hidden layers compared to ReLU?
Select an answer first
Finished these 5 questions?
Review the revealed explanations, or continue through the curriculum.
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 GIAC (SANS). “GMLE” is a trademark of its owner, used for identification only.