CS 7641 Machine Learning Final Review
2026/2027 | Complete Exam Study Guide
Single Linkage Clustering - correct answer-Treat each object as a cluster. Merge
the closest two clusters into a single cluster. Repeat n - k times.
Mutual Information - correct answer-how much does one variable say about the
other varibale; or the measure of similarity between two variables
Folk Theorem - correct answer-Any acceptable outcome can be a nash
equilibrium with the appropriate discount factor
k-means Clustering - correct answer-Pick random k cluster centers. Asssociate
each point with the closest cluster center. Recompute centers by averaging,
repeat until convergence. This converges to a local minima, error decreases, but
can get stuck. Best to do repeated attempts.
Soft Clustering - correct answer-Assigning probability to points during clustering
Expectation Maximization - correct answer-Performs Expecation: Soft Cluserting
"Likelihood data i element comes from cluster j". Maximization: Calculating
means of clusters. Can allow overlaps of clusters, can get stuck, does not converge
, Cluster Properties - correct answer-Richness, Scale-invariance, Consistency
Richness - correct answer-There is some distance metric D such that any
clustering can work
Scale-Invariance - correct answer-The cluster assignments do not change if we
change the scale (e.g. miles vs kilometers)
Consistency - correct answer-Shrinking/expanding intracluster distances does not
change the clustering
Impossibility Theorem - correct answer-No clustering scheme can achieve all
three of: richness, scale-invarance, and consistency.
Filtering - correct answer-Reduce Feature set and then apply learning. Is fast, can
use things like variance, entropy, decision trees, etc.. Can look at labels
Wrapping - correct answer-Use Learning to reduce feature set. Much slower than
filtering. Examples are Randomized Optimization algos, forward search and
backward search
Forward Search - correct answer-Enumerate the features and choose the best
combination of features (e.g. use feature 1 and 3 and test, then 1 and 5, then 2
and 4, etc...)
Backward Search - correct answer-Start with all features and iteratively drop the
most useless one
2026/2027 | Complete Exam Study Guide
Single Linkage Clustering - correct answer-Treat each object as a cluster. Merge
the closest two clusters into a single cluster. Repeat n - k times.
Mutual Information - correct answer-how much does one variable say about the
other varibale; or the measure of similarity between two variables
Folk Theorem - correct answer-Any acceptable outcome can be a nash
equilibrium with the appropriate discount factor
k-means Clustering - correct answer-Pick random k cluster centers. Asssociate
each point with the closest cluster center. Recompute centers by averaging,
repeat until convergence. This converges to a local minima, error decreases, but
can get stuck. Best to do repeated attempts.
Soft Clustering - correct answer-Assigning probability to points during clustering
Expectation Maximization - correct answer-Performs Expecation: Soft Cluserting
"Likelihood data i element comes from cluster j". Maximization: Calculating
means of clusters. Can allow overlaps of clusters, can get stuck, does not converge
, Cluster Properties - correct answer-Richness, Scale-invariance, Consistency
Richness - correct answer-There is some distance metric D such that any
clustering can work
Scale-Invariance - correct answer-The cluster assignments do not change if we
change the scale (e.g. miles vs kilometers)
Consistency - correct answer-Shrinking/expanding intracluster distances does not
change the clustering
Impossibility Theorem - correct answer-No clustering scheme can achieve all
three of: richness, scale-invarance, and consistency.
Filtering - correct answer-Reduce Feature set and then apply learning. Is fast, can
use things like variance, entropy, decision trees, etc.. Can look at labels
Wrapping - correct answer-Use Learning to reduce feature set. Much slower than
filtering. Examples are Randomized Optimization algos, forward search and
backward search
Forward Search - correct answer-Enumerate the features and choose the best
combination of features (e.g. use feature 1 and 3 and test, then 1 and 5, then 2
and 4, etc...)
Backward Search - correct answer-Start with all features and iteratively drop the
most useless one
