Skip to content

FRM Part I · FRM Exam Part I · Machine Learning and Prediction

In training a deep neural network, what is the purpose of the backpropagation algorithm?

Backpropagation efficiently computes the gradient of the loss with respect to every weight by applying the chain rule backward from the output layer. Gradient descent then uses these gradients to update weights. It does not initialize weights, split data, or choose network architecture.

  1. ATo compute the gradient of the loss with respect to each weight efficiently using the chain ruleCorrect
  2. BTo randomly select the initial weights of the network
  3. CTo split the data into training and test sets
  4. DTo choose the number of hidden layers automatically

Explanation

Backpropagation applies the chain rule from the output layer back through the hidden layers to obtain the loss gradient for every weight. An optimizer such as gradient descent then uses these gradients to update the weights. It does not initialize weights, split data, or select the architecture.

Did you get it right without looking?

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

Practise Machine Learning and PredictionFree diagnostic mock

More Machine Learning and Prediction questions