ISYE 6501 Midterm 1
Study online at https://quizlet.com/_4gqr6p
1. Rows Data points are values in data tables
2. Columns The 'answer' for each data point (response/outcome)
3. Structured Data Quantitative, Categorical, Binary, Unrelated, Time Series
4. Unstructured Data Text
5. Support Vector Supervised machine learning algorithm used for both classification and re-
Model gression challenges.
Mostly used in classification problems by plotting each data item as a point
in n-dimensional space (n is the number of features you have) with the value
of each feature being the value of a particular coordinate.
Then you classify by finding a hyperplane that differentiates the 2 classes very
well. Support vectors are simply the coordinates of individual observation --
it best segregates the two classes (hyperplane / line).
6. What do you want Find values of a0, a1,...,up to am that classifies the points correctly and has
to find with a SVM the maximum gap or margin between the parallel lines.
model?
7. What should the The sum of green points should be greater than or equal to 1
sum of the green
points in a SVM
model be?
8. What should the The sum of red points should be less than or equal to -1
sum of the red
points in a SVM
model be?
9. The total sum of all green and red points should be equal to or greater than
1 because yj is 1 for green and -1 for red.
, ISYE 6501 Midterm 1
Study online at https://quizlet.com/_4gqr6p
What should the to-
tal sum of green and
red points be?
10. First principal com- PCA -- a linear combination of original predictor variables which captures
ponent the maximum variance in the data set. It determines the direction of highest
variability in the data. Larger the variability captured in first component,
larger the information captured by component. No other component can
have variability higher than first principal component.
it minimizes the sum of squared distance between a data point and the line.
11. Second principal PCA -- also a linear combination of original predictors which captures the
component remaining variance in the data set and is uncorrelated with Z¹. In other words,
the correlation between first and second component should is zero.
12. What if it's not Utilize a soft classifier -- In a soft classification context, we might add an extra
possible to sepa- multiplier for each type of error with a larger penalty, the less we want to
rate green and red accept mis-classifying that type of point.
points in a SVM
model?
13. Soft Classifier Account for errors in SVM classification. Trading off minimizing errors we
make and maximizing the margin.
To trade off between them, we pick a lambda value and minimize a combi-
nation of error and margin. As lambda gets large, this term gets large.
The importance of a large margin outweighs avoiding mistakes and classify-
ing known data points.
14. Should you scale Yes, so the orders of magnitude are approximately the same.
your data in a SVM Data must be in bounded range.
model? Common scaling: data between 0 and 1
a. Scale factor by factor
b. Linearly
Study online at https://quizlet.com/_4gqr6p
1. Rows Data points are values in data tables
2. Columns The 'answer' for each data point (response/outcome)
3. Structured Data Quantitative, Categorical, Binary, Unrelated, Time Series
4. Unstructured Data Text
5. Support Vector Supervised machine learning algorithm used for both classification and re-
Model gression challenges.
Mostly used in classification problems by plotting each data item as a point
in n-dimensional space (n is the number of features you have) with the value
of each feature being the value of a particular coordinate.
Then you classify by finding a hyperplane that differentiates the 2 classes very
well. Support vectors are simply the coordinates of individual observation --
it best segregates the two classes (hyperplane / line).
6. What do you want Find values of a0, a1,...,up to am that classifies the points correctly and has
to find with a SVM the maximum gap or margin between the parallel lines.
model?
7. What should the The sum of green points should be greater than or equal to 1
sum of the green
points in a SVM
model be?
8. What should the The sum of red points should be less than or equal to -1
sum of the red
points in a SVM
model be?
9. The total sum of all green and red points should be equal to or greater than
1 because yj is 1 for green and -1 for red.
, ISYE 6501 Midterm 1
Study online at https://quizlet.com/_4gqr6p
What should the to-
tal sum of green and
red points be?
10. First principal com- PCA -- a linear combination of original predictor variables which captures
ponent the maximum variance in the data set. It determines the direction of highest
variability in the data. Larger the variability captured in first component,
larger the information captured by component. No other component can
have variability higher than first principal component.
it minimizes the sum of squared distance between a data point and the line.
11. Second principal PCA -- also a linear combination of original predictors which captures the
component remaining variance in the data set and is uncorrelated with Z¹. In other words,
the correlation between first and second component should is zero.
12. What if it's not Utilize a soft classifier -- In a soft classification context, we might add an extra
possible to sepa- multiplier for each type of error with a larger penalty, the less we want to
rate green and red accept mis-classifying that type of point.
points in a SVM
model?
13. Soft Classifier Account for errors in SVM classification. Trading off minimizing errors we
make and maximizing the margin.
To trade off between them, we pick a lambda value and minimize a combi-
nation of error and margin. As lambda gets large, this term gets large.
The importance of a large margin outweighs avoiding mistakes and classify-
ing known data points.
14. Should you scale Yes, so the orders of magnitude are approximately the same.
your data in a SVM Data must be in bounded range.
model? Common scaling: data between 0 and 1
a. Scale factor by factor
b. Linearly
