Machine Learning

Gradient Descent

⛪ Computer Science and Engineering > Machine Learning

A comprehensive set of multiple-choice questions (MCQs) on gradient descent, an optimization algorithm used to find the minimum of a function.

➲ Gradient Descent - Quiz

Q 1: What is the range of the output values for a sigmoid function?

  • A [-inf,+ inf]
  • B [0,.5]
  • C [0,1]
  • D [0,inf]

Q 2: Problems, where discrete-valued outputs are predicted, are called?

  • A Greedy Problems
  • B Classification Problems
  • C Regression Problems
  • D Real Valued Problems

Q 3: Classification problems with just two classes are called Binary classification problems.

  • A True
  • B False

Q 4: For ____________, the error is calculated by finding the sum of squared distance between actual and predicted values.

  • A Regression
  • B Classification
  • C Clustering
  • D None of the options

Q 5: ____________ function is used as a mapping function for classification problems.

  • A Linear
  • B Sigmoid
  • C Convex
  • D Concave

Q 6: For an underfit data set, the training and the cross-validation error will be high.

  • A True
  • B False

Q 7: ____________ measures how far the predictions are from the actual values.

  • A Bias
  • B Difference
  • C Deviation
  • D Variance

Q 8: How are the parameters updated during Gradient Descent process?

  • A Sequentially
  • B Not updated
  • C One at a time
  • D Simultaneously

Q 9: ____________ controls the magnitude of a step taken during Gradient Descent.

  • A Parameter
  • B Step Rate
  • C Momentum
  • D Learning Rate

Q 10: ____________ is the line that separates y = 0 and y = 1 in a logistic function.

  • A Divider
  • B Seperator
  • C Decision Boundary
  • D None of the options

Q 11: The objective function for linear regression is also known as Cost Function.

  • A False
  • B True

Q 12: Problems that predict real values outputs are called __________

  • A Real Valued Problems
  • B Greedy Problems
  • C Regression Problems
  • D Classification Problems

Q 13: For ____________, the error is determined by getting the proportion of values misclassified by the model.

  • A Classification
  • B Regression
  • C Clustering
  • D None of the options

Q 14: When an ML Model has a high bias, getting more training data will help in improving the model.

  • A True
  • B False

Q 15: What is the advantage of using an iterative algorithm like gradient descent ? (select the best)

  • A For Nonlinear regression problems, there is no closed form solution
  • B Linear regression problems have multiple solutions
  • C Linear regression problems there is no closed form solution