Which activation function outputs values between zero and one and is common in classification?

Which activation function outputs values between zero and one and is common in classification?

• A. ReLU
• B. Tanh
• C. Sigmoid
• D. Softmax

Answer: (C)

Sigmoid is the activation that outputs values between zero and one, making it ideal for probability-style predictions in classification tasks. It uses the logistic function f(z) = 1/(1+e^{-z}), which takes any real-valued input and squashes it into the (0,1) range. This lets you interpret the network’s output as the estimated probability of the positive class in binary classification, and it’s a common final activation in binary classifiers and logistic regression. Other activations don’t produce a single probability: ReLU is non-negative and unbounded above, tanh maps to (-1,1), and Softmax, while producing numbers between 0 and 1, yields a distribution across multiple classes and is used for multi-class problems with several outputs.

Sigmoid is the activation that outputs values between zero and one, making it ideal for probability-style predictions in classification tasks. It uses the logistic function f(z) = 1/(1+e^{-z}), which takes any real-valued input and squashes it into the (0,1) range. This lets you interpret the network’s output as the estimated probability of the positive class in binary classification, and it’s a common final activation in binary classifiers and logistic regression. Other activations don’t produce a single probability: ReLU is non-negative and unbounded above, tanh maps to (-1,1), and Softmax, while producing numbers between 0 and 1, yields a distribution across multiple classes and is used for multi-class problems with several outputs.