Question 1
Which metric is most appropriate for evaluating an imbalanced classification problem?
Question 2
Which factors influence token costs when using Large Language Models? (Choose 2)
Question 3
What is the primary benefit of using immutability in functional programming?
Question 4
In enterprise RAG, how should permissions affect retrieval?
Question 5
Which AWS SageMaker capability helps reduce model training costs by using unused EC2 capacity?
Question 6
What does the vanishing gradient problem affect most?
Question 7
What is the main role of Microsoft Graph in Copilot for Microsoft 365?
Question 8
What does the term "RAG" (Retrieval-Augmented Generation) describe?
Question 9
Which approach is commonly used to mitigate bias in AI systems?
Question 10
Which of the following is NOT a common activation function in neural networks?
Question 11
Which Microsoft service provides access to OpenAI models (such as GPT-4) within the Azure infrastructure?
Question 12
What is a key benefit of transfer learning?
Question 13
In AWS SageMaker, which feature allows training models without manual server setup?
Question 14
What does the attention mechanism in transformer models primarily improve?
Question 15
Which scenario BEST fits the use of unsupervised learning?
Question 16
Which Microsoft service is primarily responsible for enforcing data security and compliance for Copilot in Microsoft 365?
Question 17
What is the primary benefit of using immutability in functional?
Question 18
Which capabilities are provided by Amazon Bedrock?
Question 19
In reinforcement learning, what does the reward function define?
Question 20
How does the vanishing gradient problem most directly impact the training of very deep neural networks?
