FRM Part I · FRM Exam Part I · Machine-Learning Methods
A network has 4 inputs, one hidden layer with 5 neurons, and 1 output neuron. Every neuron in a layer is connected to every neuron in the previous layer, and each hidden and output neuron has one bias term. How many parameters must be estimated?
The network has 31 parameters: 20 input-to-hidden weights, 5 hidden biases, 5 hidden-to-output weights and 1 output bias. Leaving out biases is the common error that produces answers such as 25 or 30.
- A31Correct
- B25
- C26
- D30
Explanation
Input-to-hidden weights: 4×5 = 20; hidden biases: 5; hidden-to-output weights: 5×1 = 5; output bias: 1. Total = 20 + 5 + 5 + 1 = 31. Omitting the output bias gives 30; omitting all biases gives 25; 26 counts only weights plus one bias.
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
- An analyst tunes a regularization penalty in a ridge-type regression. As the penalty parameter is increased from a very small value to a ver…
- A logistic regression model of default has a coefficient of 0.693 on leverage (debt-to-equity). Holding other variables constant, what is th…
- A trading desk builds an algorithm that adjusts its hedge positions daily. It receives a profit-or-loss reward after each action and, by tri…
- An analyst has a feature with values 2, 4, 6, 8 and 20 in a training sample. The analyst applies min-max scaling to the range [0, 1] using t…
- A risk team evaluates a fraud classifier where only 1% of transactions are fraudulent. A model that labels every transaction as non-fraud ac…
- A data scientist estimates a credit-scoring model with 200 candidate predictors, believing only about 15 truly matter, and wants the fitted …