CSE 575
Statistical Machine Learning
KNOWLEDGE ASSESSMENT
REVIEW
© ASU 2024/2025
,1. Multiple Choice: Which of the following is a key assumption of
the Linear Regression model?
a) Homoscedasticity
b) Heteroscedasticity
c) Multicollinearity
d) Autocorrelation
Correct Answer: a) Homoscedasticity
Rationale: Linear Regression assumes that the variance of the
error terms is constant across all levels of the independent
variables.
2. Fill-in-the-Blank: In the context of machine learning, ________
is a technique used to estimate the performance of a model on new
data.
Correct Answer: Cross-validation
Rationale: Cross-validation is used to assess how the results of a
statistical analysis will generalize to an independent data set.
3. True/False: In Support Vector Machines (SVM), the kernel trick
is used to transform data into a higher dimension where it is
linearly separable.
© ASU 2024/2025
, Correct Answer: True
Rationale: The kernel trick involves mapping data into a higher-
dimensional space to make it possible to perform linear separation
with hyperplanes.
4. Multiple Response: Select all that apply. Which of the following
are types of biases that can occur in machine learning?
a) Sample bias
b) Algorithm bias
c) Measurement bias
d) Observer bias
Correct Answers: a) Sample bias, b) Algorithm bias, c)
Measurement bias
Rationale: These biases can affect the performance and fairness
of machine learning models by influencing the data or the learning
process itself.
5. Multiple Choice: What is the purpose of the 'dropout' technique
in neural networks?
a) To add more layers to the network
b) To prevent overfitting by randomly dropping units during
training
c) To increase the speed of training
© ASU 2024/2025
Statistical Machine Learning
KNOWLEDGE ASSESSMENT
REVIEW
© ASU 2024/2025
,1. Multiple Choice: Which of the following is a key assumption of
the Linear Regression model?
a) Homoscedasticity
b) Heteroscedasticity
c) Multicollinearity
d) Autocorrelation
Correct Answer: a) Homoscedasticity
Rationale: Linear Regression assumes that the variance of the
error terms is constant across all levels of the independent
variables.
2. Fill-in-the-Blank: In the context of machine learning, ________
is a technique used to estimate the performance of a model on new
data.
Correct Answer: Cross-validation
Rationale: Cross-validation is used to assess how the results of a
statistical analysis will generalize to an independent data set.
3. True/False: In Support Vector Machines (SVM), the kernel trick
is used to transform data into a higher dimension where it is
linearly separable.
© ASU 2024/2025
, Correct Answer: True
Rationale: The kernel trick involves mapping data into a higher-
dimensional space to make it possible to perform linear separation
with hyperplanes.
4. Multiple Response: Select all that apply. Which of the following
are types of biases that can occur in machine learning?
a) Sample bias
b) Algorithm bias
c) Measurement bias
d) Observer bias
Correct Answers: a) Sample bias, b) Algorithm bias, c)
Measurement bias
Rationale: These biases can affect the performance and fairness
of machine learning models by influencing the data or the learning
process itself.
5. Multiple Choice: What is the purpose of the 'dropout' technique
in neural networks?
a) To add more layers to the network
b) To prevent overfitting by randomly dropping units during
training
c) To increase the speed of training
© ASU 2024/2025
