NCA-GENL: Generative AI and LLMsDemo

By NVIDIA · Question Mode

QuestionQ60

Core Machine Learning and AI Knowledge

When comparing the ReLU and sigmoid activation functions, which statement is correct?

  • A ReLU is less computationally efficient than sigmoid, but it is more accurate than sigmoid.
  • B ReLU is more computationally efficient, but sigmoid is better for predicting probabilities.
  • C ReLU is a linear function while sigmoid is non-linear.
  • D ReLU and sigmoid both have a range of 0 to 1.
Explanation

ReLU uses a simple thresholding operation and is generally more computationally efficient than sigmoid. Sigmoid produces outputs between 0 and 1, so it is well suited to representing predicted probabilities.

Community Discussion

No comments yet. Be the first to start the discussion!