Machine Learning Final Exam Graded A+
2 Main Families of Ensemble Methods: - ANSWER-Averaging Methods & Boosting
Methods
2 ways to reduce computational
complexity: - ANSWER-1. Reduce number of candidate itemsets (M) by
pruning the itemset lattice (Apriori algorithm).
2. Reduce number of comparisons by using advanced data structures to store the
candidate itemsets or to compress the dataset (FP-growth)
3 Approaches for Choosing the right k in kNN - ANSWER-1. The square root of the
number of training examples.
2. Test different k values against a variety of test datasets and chose the one that
performs best.
3. Use weighted voting where the closest neighbors have larger weights.
5 ways to choose the right "k" in k-means - ANSWER-• Elbow Method
• Information Criterion Approach
• Silhouette method
• Jump method
• Gap statistic
A large k... - ANSWER-reduces the impact of noisy data but increases the risk of
ignoring important patterns.
A small k... - ANSWER-makes the model susceptible to noise and/or outliers
According to the formal definition of machine learning, "A computer program is said to
learn from _______ with respect to some class of _______ and performance measure
P, if its performance at ________, as measured by P, improves with __________". -
ANSWER-experience (E), tasks (T), tasks (T), experience (E)
accuracy <- mean(test == pred)
precision <- posPredValue(as.factor(pred), as.factor(test), positive = "Yes")
recall <- sensitivity(as.factor(pred), as.factor(test), positive = "Yes")
fmeasure <- (2 * precision * recall)/(precision + recall)
kappa <- kappa2(data.frame(test, pred))$value
auc <- as.numeric(performance(roc.pred, measure = "auc")@y.values)
comparisons <- tibble(approach="Classification Tree", accuracy = accuracy, fmeasure =
fmeasure, kappa = kappa, auc = auc) - ANSWER-Creates all performance
measurements and then compares them
Actionable Association Rules - ANSWER-Rules that provide clear and useful insights
that can be acted upon.
,Adaptive Boosting (AdaBoost) (3) - ANSWER-• The Adaptive Boosting learner works by
sequentially adding weak models which are trained using weighted training data.
• Each model is assigned a stage value which corresponds to how accurate it is against
the training data.
• The prediction for the ensemble is taken as the sum of the weighted predictions of the
weak classifiers.
Adaptive boosting strengths - ANSWER-• Boosting is a relatively simple ensemble
method to implement.
• Requires less parameter tuning compared to other ensemble methods.
• Can be used with many different classifiers.
Adaptive boosting weaknesses - ANSWER-• High tendency to overfit with many weak
learners.
• Rather slow training time.
• Sensitive to noisy data and outliers.
Additive Smoothing - ANSWER-additive (or Laplace) smoothing is used to smooth the
data by adding a pseudocount α to the number of observed and unobserved cases in
order to change the expected probability so as to avoid zero-frequency problems.
Advantages of Ensembles (4) - ANSWER-• Better generalizability to future problems.
• Improved performance on massive or miniscule datasets.
• The ability to synthesize data from distinct domains.
• A more nuanced understanding of difficult learning tasks
Akaike Information Criterion (AIC) - ANSWER-An estimate of the relative information
lost by a given model: the less information a model loses, the higher the quality of the
model
Allocation function - ANSWER-dictates how much of the training data
each model receives.
Any regression analysis involves three key sets of
variables: - ANSWER-• Dependent or response variable (y).
• Independent or predictor variables (x).
• Model parameters (unknown parameters to be
estimated by the regression model).
Apriori Principle / Anti-Monotone Principle of Support - ANSWER-The support of an
itemset never exceeds that of its subsets. Therefore, if the subset of an itemset is
infrequent, then the itemset is infrequent
Area Under the Curve (AUC) - ANSWER-The AUC treats the ROC diagram as a two-
dimensional square and measures the total area under the ROC curve
, AUC ranges from 0.5 (for a classifier with no predictive value) to 1.0 (for a perfect
classifier).
As we discussed in class, the elbow method makes use of the Within Cluster Sum of
Squares (WCSS) metric to suggest the appropriate value for "k". If we keep increasing
the value for "k", what will happen to the value for WCSS? - ANSWER-It will tend
toward zero
Association rules do not imply... - ANSWER-causality, they simply imply a strong co-
occurrence relationship between items.
Association Rules Strengths (3) - ANSWER-• Capable of working with largevamounts of
transactional data.
• Rules are easy to understand.
• Useful for "data mining" and discovering unexpected patterns in data.
Association Rules Weaknesses - ANSWER-• Not very useful for small data sets.
• Separating true insight from common sense requires some
effort.
• Easy to draw misleading
conclusions from random
patterns.
At each iteration of the Boosting
process: (2) - ANSWER-1. The resampled datasets are constructed specifically to
generate complementary learners.
2. Each learner's vote is weight based on its past performance.
Automated parameter tuning - ANSWER-Rather than manually and arbitrarily choosing
values for each of a model's parameters, it is better to conduct a search to identify the
optimal combination of parameters using a choice of evaluation methods and metrics
Automated parameter tuning requires you to consider: (3) - ANSWER-1. What type of
machine learning model (and specific implementation) should be trained on the data?
2. Which model parameters can be adjusted, and how extensively should they be tuned
to find the optimal settings?
3. What criteria should be used to evaluate the models to find the best candidate?
Averaging methods - ANSWER-Independently built models with their predictions
averaged or combined by a voting scheme. They attempt to reduce the variance of a
single base estimator.
Bagging (2) - ANSWER-also known as *Bootstrap aggregating*, it is a technique that
generates a number of training datasets by bootstrap sampling the original training data.
2 Main Families of Ensemble Methods: - ANSWER-Averaging Methods & Boosting
Methods
2 ways to reduce computational
complexity: - ANSWER-1. Reduce number of candidate itemsets (M) by
pruning the itemset lattice (Apriori algorithm).
2. Reduce number of comparisons by using advanced data structures to store the
candidate itemsets or to compress the dataset (FP-growth)
3 Approaches for Choosing the right k in kNN - ANSWER-1. The square root of the
number of training examples.
2. Test different k values against a variety of test datasets and chose the one that
performs best.
3. Use weighted voting where the closest neighbors have larger weights.
5 ways to choose the right "k" in k-means - ANSWER-• Elbow Method
• Information Criterion Approach
• Silhouette method
• Jump method
• Gap statistic
A large k... - ANSWER-reduces the impact of noisy data but increases the risk of
ignoring important patterns.
A small k... - ANSWER-makes the model susceptible to noise and/or outliers
According to the formal definition of machine learning, "A computer program is said to
learn from _______ with respect to some class of _______ and performance measure
P, if its performance at ________, as measured by P, improves with __________". -
ANSWER-experience (E), tasks (T), tasks (T), experience (E)
accuracy <- mean(test == pred)
precision <- posPredValue(as.factor(pred), as.factor(test), positive = "Yes")
recall <- sensitivity(as.factor(pred), as.factor(test), positive = "Yes")
fmeasure <- (2 * precision * recall)/(precision + recall)
kappa <- kappa2(data.frame(test, pred))$value
auc <- as.numeric(performance(roc.pred, measure = "auc")@y.values)
comparisons <- tibble(approach="Classification Tree", accuracy = accuracy, fmeasure =
fmeasure, kappa = kappa, auc = auc) - ANSWER-Creates all performance
measurements and then compares them
Actionable Association Rules - ANSWER-Rules that provide clear and useful insights
that can be acted upon.
,Adaptive Boosting (AdaBoost) (3) - ANSWER-• The Adaptive Boosting learner works by
sequentially adding weak models which are trained using weighted training data.
• Each model is assigned a stage value which corresponds to how accurate it is against
the training data.
• The prediction for the ensemble is taken as the sum of the weighted predictions of the
weak classifiers.
Adaptive boosting strengths - ANSWER-• Boosting is a relatively simple ensemble
method to implement.
• Requires less parameter tuning compared to other ensemble methods.
• Can be used with many different classifiers.
Adaptive boosting weaknesses - ANSWER-• High tendency to overfit with many weak
learners.
• Rather slow training time.
• Sensitive to noisy data and outliers.
Additive Smoothing - ANSWER-additive (or Laplace) smoothing is used to smooth the
data by adding a pseudocount α to the number of observed and unobserved cases in
order to change the expected probability so as to avoid zero-frequency problems.
Advantages of Ensembles (4) - ANSWER-• Better generalizability to future problems.
• Improved performance on massive or miniscule datasets.
• The ability to synthesize data from distinct domains.
• A more nuanced understanding of difficult learning tasks
Akaike Information Criterion (AIC) - ANSWER-An estimate of the relative information
lost by a given model: the less information a model loses, the higher the quality of the
model
Allocation function - ANSWER-dictates how much of the training data
each model receives.
Any regression analysis involves three key sets of
variables: - ANSWER-• Dependent or response variable (y).
• Independent or predictor variables (x).
• Model parameters (unknown parameters to be
estimated by the regression model).
Apriori Principle / Anti-Monotone Principle of Support - ANSWER-The support of an
itemset never exceeds that of its subsets. Therefore, if the subset of an itemset is
infrequent, then the itemset is infrequent
Area Under the Curve (AUC) - ANSWER-The AUC treats the ROC diagram as a two-
dimensional square and measures the total area under the ROC curve
, AUC ranges from 0.5 (for a classifier with no predictive value) to 1.0 (for a perfect
classifier).
As we discussed in class, the elbow method makes use of the Within Cluster Sum of
Squares (WCSS) metric to suggest the appropriate value for "k". If we keep increasing
the value for "k", what will happen to the value for WCSS? - ANSWER-It will tend
toward zero
Association rules do not imply... - ANSWER-causality, they simply imply a strong co-
occurrence relationship between items.
Association Rules Strengths (3) - ANSWER-• Capable of working with largevamounts of
transactional data.
• Rules are easy to understand.
• Useful for "data mining" and discovering unexpected patterns in data.
Association Rules Weaknesses - ANSWER-• Not very useful for small data sets.
• Separating true insight from common sense requires some
effort.
• Easy to draw misleading
conclusions from random
patterns.
At each iteration of the Boosting
process: (2) - ANSWER-1. The resampled datasets are constructed specifically to
generate complementary learners.
2. Each learner's vote is weight based on its past performance.
Automated parameter tuning - ANSWER-Rather than manually and arbitrarily choosing
values for each of a model's parameters, it is better to conduct a search to identify the
optimal combination of parameters using a choice of evaluation methods and metrics
Automated parameter tuning requires you to consider: (3) - ANSWER-1. What type of
machine learning model (and specific implementation) should be trained on the data?
2. Which model parameters can be adjusted, and how extensively should they be tuned
to find the optimal settings?
3. What criteria should be used to evaluate the models to find the best candidate?
Averaging methods - ANSWER-Independently built models with their predictions
averaged or combined by a voting scheme. They attempt to reduce the variance of a
single base estimator.
Bagging (2) - ANSWER-also known as *Bootstrap aggregating*, it is a technique that
generates a number of training datasets by bootstrap sampling the original training data.
