FRM Part I · FRM Exam Part I · Machine-Learning Methods
A neuron has two inputs x1 = 2 and x2 = -1, weights w1 = 0.5 and w2 = 1.5, and bias b = 0.25. The neuron uses a ReLU activation, f(z) = max(0, z). What is its output?
The output is 0. The weighted sum plus bias is 0.5×2 + 1.5×(-1) + 0.25 = -0.25, which is negative, and a ReLU activation returns zero for any negative input.
- A0Correct
- B-0.25
- C0.25
- D1.25
Explanation
Compute z = 0.5(2) + 1.5(-1) + 0.25 = 1.0 - 1.5 + 0.25 = -0.25. ReLU returns max(0, -0.25) = 0. The option -0.25 forgets to apply ReLU, and 1.25 results from ignoring the sign of x2 (1.0 + 1.5 - 1.0... or treating it as positive).
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
- A LASSO model minimizes the sum of squared residuals plus lambda times the sum of absolute coefficients. A model has coefficients 2.0, -1.5,…
- A risk analyst is building a model to predict loan defaults using features such as annual income (in thousands of dollars, ranging 20 to 500…
- A risk team has a training sample of 1,000 observations for a credit scoring model. A feature 'missing_income' is present for 10% of records…
- A logistic regression for default has the form ln(p/(1-p)) = -3.0 + 0.5 x, where x is the debt-to-income ratio expressed in percentage point…
- For a given prediction model, the squared bias at a point is 0.04, the variance of the model's prediction is 0.09, and the irreducible error…
- A bank's credit model classifies 200 loan applicants as likely defaulters or non-defaulters. The confusion matrix shows 40 true positives (d…