FRM Part I · FRM Exam Part I · Machine-Learning Methods
A hidden node in a neural network receives three inputs x1 = 2, x2 = -1 and x3 = 3 with weights 0.5, 2.0 and -0.4 respectively, and a bias of 0.6. The node uses a ReLU activation, f(z) = max(0, z). What is the node's output?
The output is 0.00. The weighted sum plus bias is 1 - 2 - 1.2 + 0.6 = -1.6, which is negative. A ReLU activation returns the maximum of zero and the input, so the negative pre-activation is set to zero.
- A0.00Correct
- B-0.60
- C0.40
- D1.00
Explanation
z = 0.5(2) + 2.0(-1) + (-0.4)(3) + 0.6 = 1 - 2 - 1.2 + 0.6 = -1.6. ReLU returns max(0, -1.6) = 0. The value -1.6 is the pre-activation, and omitting the bias or mis-signing terms gives the other values.
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.
More Machine-Learning Methods questions
- In the logistic regression ln(p/(1-p)) = b0 + b1 x with b1 = 0.693, how does a one-unit increase in x affect the odds of the positive class,…
- A risk manager lowers the probability threshold at which a logistic model classifies a borrower as a defaulter, from 0.50 to 0.30. Which out…
- An analyst standardizes a feature using the training sample mean of 12 and a training standard deviation of 4. A new observation in the test…
- A trading desk builds an algorithm that repeatedly chooses how much of a position to execute each minute. After each action it observes the …
- A risk analyst builds a feedforward neural network to predict loan default. Which statement best describes the role of the activation functi…
- A risk analyst fits a single classification tree to predict loan default and lets it grow until every training observation sits in a pure le…