Skip to content

FRM Part I · FRM Exam Part I · Machine-Learning Methods

A risk analyst builds a feedforward neural network to predict loan default. Which statement best describes the role of the activation function in a hidden layer?

The activation function introduces nonlinearity into a hidden layer. Without it, multiple layers of weighted sums would reduce to one linear transformation, so the network could not capture nonlinear relationships such as interactions between borrower characteristics and default probability.

  1. AIt introduces nonlinearity so the network can model relationships a linear combination of inputs cannotCorrect
  2. BIt rescales the target variable so that its mean is zero and its variance is one
  3. CIt selects which input features are removed from the model before training starts
  4. DIt sets the learning rate used when the weights are updated

Explanation

Each hidden neuron computes a weighted sum of inputs and passes it through an activation function. Without a nonlinear activation, stacked layers would collapse into a single linear model. The other options describe feature scaling, feature selection and learning-rate choice, which are not activation functions.

Did you get it right without looking?

One question tells you little. A timed set on Machine-Learning Methods shows your real accuracy, how long you take and where you lose marks.

Practise Machine-Learning MethodsFree diagnostic mock

More Machine-Learning Methods questions