ISYE-6501 Exam 1
Questions and Answers
Denning [Date] [Course title]
,Algorithm - Correct Answers:s :a step-by-step procedure designed to carry out a task
Change Detection - Correct Answers:s :Identifying when a significant change has taken place
Classification - Correct Answers:s :Separation of data into two or more categories
Classifier - Correct Answers:s :A boundary that separates data into two or more categories
Cluster - Correct Answers:s :A group of points that are identified as being similar or near each other
Cluster Center - Correct Answers:s :In some clustering algorithms (k-means), the central point of a
cluster center (CENTROID)
Clustering - Correct Answers:s :Separation of points into similar or near groupings. Form of unsupervised
learning.
CUSUM - Correct Answers:s :change detection method that compares observed distribution mean with a
threshold level of change. Short for Cumulative Sum (also cumsum)
Deep Learning - Correct Answers:s :Neural Network model with many hidden layers
Dimension - Correct Answers:s :A feature of the data points.
EM Algorithm - Correct Answers:s :Expectation Maximization Algorithm. Algorithm with two steps (often
iterated).
1. Finds the function for the expected likelihood of getting the response given current parameters.
2. Finds new parameter values that maximize probability
Heuristic - Correct Answers:s :Algorithm that isn't guaranteed to find the optimal solution
, K-means - Correct Answers:s :Clustering algorithm (unsupervised), that works by defining k centroids
and then mapping each point to the closest centroid.
K-nearest neighbor (K-NN) - Correct Answers:s :Classification algorithm (supervised), that works by
mapping a data point to the k closest neighbors to it.
Kernel - Correct Answers:s :A type of function that computes the similarity between two inputs. thanks
to what's sometimes known as the "kernel trick", non-linear classifiers can be found almost as easily as
linear ones. Helps represent higher dimensional data sets.
Learning - Correct Answers:s :Finding/discovering new patterns in data that can be applied to new data
Machine - Correct Answers:s :Apparatus that can do something. in ml it often refers to the algorithm
and the computer is run on.
Margin - Correct Answers:s :for a single point, the distance between the point and the classification
boundary; for a set of points the minimum distance between a point in the set and the classification
boundary; Also called separation.
Machine Learning - Correct Answers:s :Use of computer algorithms to learn and discover patterns or
structure in data, without being programmed specifically for them.
Misclassified - Correct Answers:s :To put a data point in the wrong category by a classifier
Neural Network - Correct Answers:s :A machine learning model that itself is modeled after the workings
of neurons in the brain.
Supervised Learning - Correct Answers:s :Machine learning where the "correct" answer is known for
each data point in the training set.
Support Vector - Correct Answers:s :In SVM models, the point closest to the classifier, among those in
the category.
Questions and Answers
Denning [Date] [Course title]
,Algorithm - Correct Answers:s :a step-by-step procedure designed to carry out a task
Change Detection - Correct Answers:s :Identifying when a significant change has taken place
Classification - Correct Answers:s :Separation of data into two or more categories
Classifier - Correct Answers:s :A boundary that separates data into two or more categories
Cluster - Correct Answers:s :A group of points that are identified as being similar or near each other
Cluster Center - Correct Answers:s :In some clustering algorithms (k-means), the central point of a
cluster center (CENTROID)
Clustering - Correct Answers:s :Separation of points into similar or near groupings. Form of unsupervised
learning.
CUSUM - Correct Answers:s :change detection method that compares observed distribution mean with a
threshold level of change. Short for Cumulative Sum (also cumsum)
Deep Learning - Correct Answers:s :Neural Network model with many hidden layers
Dimension - Correct Answers:s :A feature of the data points.
EM Algorithm - Correct Answers:s :Expectation Maximization Algorithm. Algorithm with two steps (often
iterated).
1. Finds the function for the expected likelihood of getting the response given current parameters.
2. Finds new parameter values that maximize probability
Heuristic - Correct Answers:s :Algorithm that isn't guaranteed to find the optimal solution
, K-means - Correct Answers:s :Clustering algorithm (unsupervised), that works by defining k centroids
and then mapping each point to the closest centroid.
K-nearest neighbor (K-NN) - Correct Answers:s :Classification algorithm (supervised), that works by
mapping a data point to the k closest neighbors to it.
Kernel - Correct Answers:s :A type of function that computes the similarity between two inputs. thanks
to what's sometimes known as the "kernel trick", non-linear classifiers can be found almost as easily as
linear ones. Helps represent higher dimensional data sets.
Learning - Correct Answers:s :Finding/discovering new patterns in data that can be applied to new data
Machine - Correct Answers:s :Apparatus that can do something. in ml it often refers to the algorithm
and the computer is run on.
Margin - Correct Answers:s :for a single point, the distance between the point and the classification
boundary; for a set of points the minimum distance between a point in the set and the classification
boundary; Also called separation.
Machine Learning - Correct Answers:s :Use of computer algorithms to learn and discover patterns or
structure in data, without being programmed specifically for them.
Misclassified - Correct Answers:s :To put a data point in the wrong category by a classifier
Neural Network - Correct Answers:s :A machine learning model that itself is modeled after the workings
of neurons in the brain.
Supervised Learning - Correct Answers:s :Machine learning where the "correct" answer is known for
each data point in the training set.
Support Vector - Correct Answers:s :In SVM models, the point closest to the classifier, among those in
the category.
