H13-311_V3.5 · Question #339
What are the commonly used activation functions? (Multiple Choice)
The correct answer is A. sigmoid B. tanh C. relu. Sigmoid, tanh, and ReLU (Rectified Linear Unit) are the three foundational activation functions in neural networks - each introduces non-linearity that allows networks to learn complex patterns. Sigmoid squashes outputs to (0,1), making it useful for binary classification; tanh…
Question
What are the commonly used activation functions? (Multiple Choice)
Options
- Asigmoid
- Btanh
- Crelu
- Ddanish
How the community answered
(30 responses)- A77% (23)
- D23% (7)
Explanation
Sigmoid, tanh, and ReLU (Rectified Linear Unit) are the three foundational activation functions in neural networks - each introduces non-linearity that allows networks to learn complex patterns. Sigmoid squashes outputs to (0,1), making it useful for binary classification; tanh squashes to (-1,1) and is zero-centered, which often helps gradient flow; ReLU simply outputs max(0, x) and is the most widely used today due to its computational efficiency and resistance to vanishing gradients. "Danish" (D) is not a mathematical function at all - it's a pastry, included as an obvious distractor.
Memory tip: Think STR - Sigmoid, Tanh, ReLU - the three classics. If an answer choice sounds like food, skip it.
Topics
Community Discussion
No community discussion yet for this question.