QuestionQ93

VerifiedML – Neural Networks and Testing

Which ONE of the following is NOT an input to an activation function in a neural network?

Explanation

An activation function computes its output from the weighted sum of the previous layer's activations plus a bias term (z = Σ(weight × previous-layer activation) + bias), and this sum is then passed through the activation function to produce the current layer's activation. Because the current layer's activation values are the result of applying the activation function, they cannot also serve as an input to it — that would be circular. The bias, the weights on the connections, and the previous layer's activation values are the actual inputs used to compute this sum.

Community Discussion

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