Linear Models Flashcards
Definition of Linear (affine) functions and its hypothesis classes. Equivalent notation too.
2 / 2-4
Definition of halfspace. When it is used?
2 / 5
When data are linearly separable?
2 / 6 or 7 / 4
Perceptron for halfspaces (describe the algorithm). When the algorithm stop?
2 / 7-8
For Linear Regression what is hypothesis class, loss function and empirical risk
2 / 20-21
In Linear regression, what is least squares? Also write the equivalent formulation RSS. What the acronym means?
2 / 22
RSS in matrix form. How to find the solution of that minimizes RSS? What if the matrix is not invertible?
2 / 23-27 no 26
What is feature normalization? Why is it important?
2 / 38
Logistic regression : What it is? For what is used for? What is its hypothesis class?
2 / 39-41
Logistic regression : What are the differences with halfspaces?
2 / 41
Which is the loss function used in logistic regression models?
2 / 42-43
What is the ERM problem for the Logistic regression? How can be solved?
2 / 44
Only define what is the MLE?
2 / 45
Describe the general approach to find the MLE? (NO part on logistic regression)
2 / 45
Logistic regression and MLE, describe it. The MLE found at the end, is it similar to another approach we have studied?
2 / 46-47
Coefficient of determination R^2 : definition and interpretation
2 / 31
GD algortihm (pseudocode)
2 / 12
Describe the stochastic gradient descent (SGD) algorithm (in general).
2 / 13
What is the
main advantage of SGD with respect to the gradient descent algorithm?
2 / 15
SGD for linear classification
2 / 16-18
Compare the perceptron and the SGD perceptron. How can the SGD perceptron be speed up?
2 / 19
