Reading questions

Machine learning questions:

• What is a learning algorithm?
• What is the difference between the training, validation and test sets?
• What is supervised learning?
• What is unsupervised learning?
• What is empirical risk minimization?
• What is stochastic gradient descent?
• What is the capacity of a model?
• What is the difference between a parametric and a non-parametric model?
• What is the difference between a parameter and a hyper-parameter?
• What is generalization?
• What is the difference between under-fitting and over-fitting?
• What is model selection?
• What is regularization?
• What is the bias variance trade-off?

Differential calculus:

• What is a derivative?
• What is a partial derivative?
• What is a gradient?
• What is the chain rule?
• What is a Hessian matrix?

Linear algebra review:

• What is a matrix? What is a vector?
• How to perform products between matrices and vectors?
• What are the following properties of matrices?
  • identity matrix
  • diagonal matrix
  • transpose matrix
  • symmetric matrix
  • orthogonal matrix
  • positive semidefinite matrix
• What are the following operations on a matrix and their properties?
  • trace of a matrix
  • norm of a matrix
  • inverse of a matrix
  • determinant of a matrix
• What is the concept of linear dependance between vectors?
• What is the rank of a matrix?
• What are the range and nullspace of a matrix?
• What are the eigenvalues and eigenvectors of a matrix, and what are their properties?
• How does the concept of gradient generalize to vectors and matrices?

Probability review

• What is a probability space?
• What is a random variable?
• What is a distribution?
• What is are joint, marginal and conditional distributions?
• When are random variables independent?
• What is the probability chain rule?
• What is the Bayes rule?
• What is the difference between a discrete and continuous distribution?
• What is are density and cumulative distribution functions?
• What are the expectation and variance of a random variable?
• What are the Bernoulli, Poisson and Gaussian distributions?
• What is Jensen's Inequality?

Statistics review:

• How to estimate the expectation or variance of a random variable from samples?
• What is a confidence interval?

Sampling review:

• What is a simple Monte Carlo estimate?
• What is direct sampling?
• What is rejection sampling?
• What is importance sampling?
• What is Markov Chain Monte Carlo?
• What is Metropolis Hastings?
• What is Gibbs sampling?

Python:

• What is the Python interpreter?
• How to manipulate numbers and strings in Python?
• What is the syntax of control flow statements (if, for, etc.) in Python?
• How to use the common data structures (Lists, Tuples, Sets and Dictionaries) in Python?
• How to define functions and classes?
• What are modules and packages?
• How to read and write in files?
• What is and how to use Pickle (and cPickle)?
• How to do linear algebra with Numpy?
• How to debug in Python?

MLPython:

• How to download and load a dataset?
• What are MLProblems and how to manipulate them?
• What are Learners?
• How to perform a machine learning experiment with MLPython?