Math for Data Science Proficiency

  • 30m
  • 20 questions
The Math for Data Science Proficiency benchmark will measure your ability to recall, relate, analyze, and apply the underlying math concepts in data science solutions and machine learning algorithms. You will be evaluated on your ability to recognize, analyze, and apply the advanced math concepts in machine learning algorithms such as statistics, probability, linear algebra and calculus, algorithm tuning techniques and optimization techniques, and the math behind complex algorithms like decision trees and recommendation systems . A learner who scores high on this benchmark demonstrates that they have the proficiency to apply advanced math concepts to develop efficient machine learning solutions.

Topics covered

  • apply Poisson distributions to make estimates in real-life situations
  • apply the ANOVA test for multiple groups
  • build a logistic regression model using principal components
  • calculate skewness and kurtosis on real data
  • calculate the Euclidean and Manhattan distance between two points using SciPy as well as your own function
  • code the steps to apply gradient descent to find the optimum hyperplane
  • compute a penalty for a large number of latent factors when computing the factors of a ratings matrix
  • compute eigenvalues and eigenvectors
  • compute the predicted ratings given by users for various items by using matrix decomposition
  • compute the shortest path and a minimum spanning tree for a graph
  • create naive Bayes models in Python
  • create probability tables for a Bayesian network
  • describe how unstable gradients can be mitigated using variants of the ReLU activation function
  • estimate a population's mean with confidence intervals
  • explore and perform stochastic gradient descent
  • illustrate the use of decision trees for continuous values
  • implement regression models using libraries
  • outline how to create balanced samples from an imbalanced dataset
  • use two-way ANOVA with interaction between the independent variables
  • work through a calculation of an epoch