Question 1
0.1 out of 0.1 points
ROC stands for
Selected Answer:
Correctd.
Receiver Operating Characteristics
Answers:
a.
Return Operation Curve
b.
Receiver Operating Curve
c.
Rapid Operating Curve
Correctd.
Receiver Operating Characteristics
Question 2
0.1 out of 0.1 points
In holdout method, the given data is randomly partitioned into _____ independent sets.
Selected Answer:
Correctb.
two
Answers:
a.
one
Correctb.
two
c.
many
d.
none of the above
Question 3
0.1 out of 0.1 points
If an object has deviated significantly from the data set based on certain conditions such as time or location, it is considered which type of outlier?
Selected Answer:
Correcta.
Contextual Outlier
Answers:
Correcta.
Contextual Outlier
b.
Global Outlier
c.
Collective Outlier
d.
Not an outlier
Question 4
0.1 out of 0.1 points
Which one of the following is the major category of clustering methods for high-dimensional data
Selected Answer:
Correctb.
Dimensionality reduction methods
Answers:
a.
Statistical methods
Correctb.
Dimensionality reduction methods
c.
Bagging
d.
Normalization
Question 5
0 out of 0.1 points
The minimum eccentricity of all vertices is called
Selected Answer:
Incorrectb.
Radius
Answers:
Correcta.
Eccentricity
b.
Radius
c.
Diameter
d.
Peripheral Vertex
Question 6
0.1 out of 0.1 points
____________ is called structural-context similarity.
Selected Answer:
Correctc.
SimRank
Answers:
a.
In-Neighborhood
b.
out-neighborhood
Correctc.
SimRank
d.
Distance
Question 7
0.1 out of 0.1 points
____________ is a density-based clustering Method.
Selected Answer:
Correctd.
All the above
Answers:
a.
DBSCAN
b.
OPTICS
c.
DENCLUE
Correctd.
All the above
Question 8
0.1 out of 0.1 points
A ________________ is a tree like diagram that graphically displays hierarchical clustering
Selected Answer:
Correcta.
dendrogram
Answers:
Correcta.
dendrogram
b.
decision tree
c.
histogram
d.
None of the above
Question 9
0.1 out of 0.1 points
Clustering is an approach that uses which learning technique:
Selected Answer:
Correcta.
By Observation
Answers:
Correcta.
By Observation
b.
By examples
c.
By listening
d.
All of above
Question 10
0.1 out of 0.1 points
Bayesian belief networks (BBN) differ from naïve Bayesian classifiers (BC) in that :
Selected Answer:
Correctb.
BCs assume the values of the attributes in a tuple are conditionally independent, while BBNs do not make that assumption
Answers:
a.
BBNs are always more computationally more efficient than are BCs
Correctb.
BCs assume the values of the attributes in a tuple are conditionally independent, while BBNs do not make that assumption
c.
BCs are always more accurate, even when the data tuples have attribute values that are not necessarily conditionally independent
d.
No significant differences exist
Question 11
0.1 out of 0.1 points
In ___________ each cluster is represented by one of the objects of the cluster located near the center.
Selected Answer:
Correcta.
k-medoid
Answers:
Correcta.
k-medoid
b.
k-means
c.
STIRR
d.
ROCK
Question 12
0.1 out of 0.1 points
_________________ is a two steps process model that describes and distinguishes data classes or concepts.
Selected Answer:
Correctc.
Data Classification
Answers:
a.
Data selection
b.
Data Characterization
Correctc.
Data Classification
d.
Data discrimination
Question 13
0 out of 0.1 points
K-mean is a
Selected Answer:
Incorrectd.
None of the above
Answers:
a.
Method for creating clusters based on similarities amongst members of a cluster
b.
Method for clustering that requires an initial value, k, that predetermines the number of clusters to create from a given data set
Correctc.
Both a and b
d.
None of the above
Question 14
0.1 out of 0.1 points
Less time in training but more time in predicting
Selected Answer:
Correcta.
Lazy Learning
Answers:
Correcta.
Lazy Learning
b.
Eager Learning
c.
a and b
d.
None of the above
Question 15
0.1 out of 0.1 points
Hierarchical clustering methods
Selected Answer:
Correctc.
Start either with individual objects as clusters or with the entire data set as a single cluster
Answers:
a.
Are always top-down in their approach to forming hierarchies
b.
Are impervious to the choice of split / merge points
Correctc.
Start either with individual objects as clusters or with the entire data set as a single cluster
d.
All of the above