TU Wien:Machine Learning VU (Musliu)/Exam 2021-01-25

SVM with gradient descent always finds the optimal hyperplane - False
Gradient descent always finds the global optimum - False
A RNN can be unrolled into an infinite fully connected network - True
Pooling and convolution are operations related to RNNs - False
Learning the structure of a bayesian network is less complex than learning the probabilities - False
SVMs with a linear kernel are especially good for high-dimensional data - True
Random forest is a homogeneous ensemble method - True
If you use use several weak learners h with boosting to get a classifier H and all h are linear classifiers, then H is also a linear classifier - False

Explain difference between L2 and L1 regularization
Explain implications of no free lunch theorem
Decision tree stump example with boosting
Depth of decision tree with 1000 samples and max 300 samples per leave
Explain polynomial regression, name advantages and disadvantages compared to linear regression

Navigationsmenü