Data Analytics Quiz 3

SVM can be used to solve ___________ problems.

• Classification

• Regression

• Clustering

• Both Classification and Regression

The training examples closest to the separating hyperplane are called as _______

• Training vectors

• Test vectors

• Support vectors

• Discriminant vectors

Based on the form of error function, SVM models can be classified into which of the following?

• C-SVM classification

• Nu-SVM Classification

• Epsilon-SVM regression

• nu-SVM regression

• All of the above

Which of the following SVM model can be used to detect the outliers?

• nu-SVM classification

• nu-SVM regression

• one-classification

• None of the above

The effectiveness of an SVM depends upon:

• Selection of Kernel

• Kernel Parameters

• Soft Margin Parameter C

• All of the above

The F statistic for testing the statistical significance of the overall regression model is given by______________.

• MSR/MSE

• MSE/MSR

• SSR/SSE

• SSE/SSR

Hierarchical clustering should be primarily used for exploration.

• True

• False

K-means is not deterministic and it also consist of number of iterations.

• True

• False

Point out the correct statement:

• The choice of an appropriate metric will influence the shape of the clusters.

• Hierarchical clustering is also called HCA

• In general, the merges and splits are determined in a greedy manner.

• All of the Mentioned

Which of the following is finally produced by Hierarchical Clustering ?

• Final estimate of cluster centroids

• Tree showing how close things are to each other

• Assignment of each point to clusters

• All of the mentioned