Font size
WorksheetsMachine Learning Quiz
Total questions: 100
Worksheet time: 50mins
is a field of computer science that deals with system programming to learn and improve with experience.
Artifical Intelligence
Machine learning
Data Mining
Model Selection
The process of choosing models among diverse mathematical models, which are used to define the same data set is known as
Model Selection
Data Mining
Artifical Intelligence
Machine learning
Machine learning is The autonomous acquisition of knowledge through the use of computer programs
The autonomous acquisition of knowledge through the use of manual
The selective acquisition of knowledge through the use of computer programs
The selective acquisition of knowledge through the use of manual programs
The autonomous acquisition of knowledge through the use of computer programs
Who provided a formal definition of machine learning?
Tom A. Mitchell
Tom M. Mitchell
Tom K. Mitchell
Tom J. Mitchell
Machine learning is divided into how many categories?
2
3
4
5
Inputs are divided into how many in Classifications?
2
3
4
5
What happens in clustering?
An exponential of the inputs is found
Inputs are multiplied
Inputs are divided into groups
Sets are multiplied
Computers are best at learning ______
facts
concepts
procedures
principles
Data used to build a data mining model.
validation data
training data
test data
hidden data
Data used to optimize the parameter settings of a supervised learner model.
training
test
verification
validation
The average squared difference between classifier predicted output and actual output.
mean squared error
root mean squared error
mean absolute error
mean relative error
The process of forming general concept definitions from examples of concepts to be learned.
deduction
abduction
induction
conjunction
Data mining is best described as the process of __________ identifying patterns in data.
deducing relationships in data.
representing data.
simulating trends in data.
identifying patterns in data.
Computers are best at learning ______
facts
concepts
procedures
principles
Like the probabilistic view, the ______ view allows us to associate a probability of membership with each classification.
exemplar
deductive
classical
inductive
______ used to build a data mining model.
validation data
training data
test data
hidden data
Supervised learning and unsupervised clustering both require at least one hidden attribute.
output attribute
input attribute
categorical attribute
input attribute
Supervised learning differs from unsupervised clustering in that supervised learning requires ______ at least one input attribute.
input attributes to be categorical.
at least one output attribute.
output attributes to be categorical.
at least one output attribute.
Database query is used to uncover this type of knowledge________.
deep
hidden
shallow
multidimensional
______ is a statement to be tested.
theory
procedure
principle
hypothesis
______ is a person trained to interact with a human expert in order to capture their knowledge.
knowledge programmer
knowledge developer
knowledge engineer
knowledge extractor
Which of the following is not a characteristic of a data warehouse?
contains historical data
designed for decision support
stores data in normalized tables
promotes data redundancy
______ is a structure designed to store data for decision support.
operational database
flat file
decision tree
data warehouse
A nearest neighbor approach is best used _______ with large-sized datasets.
when irrelevant attributes have been removed from the data.
when a generalized model of the data is desirable.
when an explanation of what has been found is of primary importance.
when irrelevant attributes have been removed from the data.
If a customer is spending more than expected, the customer’s intrinsic value is
their actual value.
greater than
less than
less than or equal to
can be any unprocessed fact, value, text, sound or picture that is not being interpreted and analyze
data
knowledge
information
machine
has been interpreted and manipulated
data
knowledge
information
machine
________is the combination of inferred information and learning.
data
knowledge
information
machine
model
training data
testing data
validation data
knowledge
How we split data in Machine Learning?
3
5
6
8
means scale of data.
volume
value
velocity
veracity
Which defined correctness in data?
volume
value
velocity
veracity
Supervised Learning is also called as .
Inductive Learning
semi-supervised
regression
labeled
Which dataset is one which has both input and output parameters?
labeled
unlabelled
function model
labeled
What is another name for meaningless data?
unstructured data
structured data
labeled data
value
The data which contains only an input parameters.
unstructured data
structured data
unlabeled data
value
is a classification algorithm for binary and multi class classification problems.
naïve bayes
bayes
stephen
bias
is a sub-field of mathematics concerned with vectors, matrices, and linear
linear algebra
linear graphs
linear arrays
linear matrix
_____is a method of teaching and learning in a logical manner.
Machine learning
PAC Learning
Artifical Intelligence
Sequence learning
is about identifying group membership while regression technique involves predicting a response
Classification
Association
Regression models
Clustering
Which training data includes a few desired outputs?
Inductive Learning
semi-supervised
regression
labeled
The way candidate programs are generated known as the process.
search
hypothesis
evaluation
knowledge
Which is called as idiot?
naive
naive bayes
bias
flemming bayes
The field of study that gives computers the capability to learn without being explicitly programmed is known as .
machine learning
data learning
testing learning
type learning
defined labels.
classification
regression
supervised learning
data warehouse
Predictive models having target attribute having discrete values can be termed as
Regression models
Classification models
supervised learning
data warehouse
When was the name coined?
1987
1959
1978
1990
is based on an assumption that all of the features in the data set are important, equal and independent.
naive
naive bayes
bias
flemming bayes
is a process or a study whether it closely relates to design, development of the algorithms that provide an ability to the machines to capacity to learn.
Model Selection
Data Mining
Artifical Intelligence
Machine learning
technique is a rule based ML technique which finds out some very useful relations between parameters of a large data set.
Classification models
Association
Regression models
data warehouse
technique is mostly applicable in case of image data-sets where usually all images are not labeled.
Inductive Learning
semi-supervised
regression
labeled
model keeps on increasing its performance using a Reward Feedback to learn the behavior or pattern.
supervised
semi-supervised
reinforcement
unsupervised
Which is example of supervised learning algorithm?
K-Means Clustering
Decision Trees
Temporal Difference (TD)
Q-Learning
With Bayes classifier, missing data items are treated as equal
compares.
treated as unequal
replaced with a default value.
ignored.
This unsupervised clustering algorithm terminates when mean values computed for the current iteration of the algorithm are identical to the computed mean values for the previous iteration.
agglomerative clustering
conceptual clustering
K-Means clustering
expectation maximization
MATLAB stands for
Maths Laboratory
Matrix Laboratory
Mathematical Lab
Maths Lab
MATLAB was developed by
MathsWorks
Intel
Microsoft
IBM
In MATLAB the matrix is defined as an
vector
scalar
array
integer
________acts as an outstanding tool for visulaizing technical data
C
C++
Java
MATLAB
In command window the are entered
data
values
commands
files
window displays plots and graphs
command
Edit
Figure
Command history
The term is used to describe an array with two or more dimensions
array
vector
matrix
scale
In MATLAB, the process of replacing loops by vectorized statements is known as
scalarization
vectorization
looping
branching
What do you mean by a hard margin?
The SVM allows very low error in classification
The SVM allows high amount of error in classification
The SVM is not allow very low error in classification
The SVM allows medium amount of error in classification
The minimum time complexity for training an SVM is O(n2). According to this fact, what sizes of datasets are not best suited for SVM’s?
Large datasets
Small datasets
Medium sized datasets
Size does not matter
The effectiveness of an SVM depends upon:
Selection of Kernel
Kernel Parameters
Soft Margin Parameter C
All of the above
Suppose you are using RBF kernel in SVM with high Gamma value. What does this signify?
The model would consider even far away points from hyperplane for modeling
The model would consider only the points close to the hyperplane for modeling
The model would not be affected by distance of points from hyperplane for modeling
None of the above
What would happen when you use very small C (C~0)?
Misclassification would happen
Data will be correctly classified
Can’t say
None of these
Suppose you gave the correct answer in previous question. What do you think that is actually happening?
1. We are lowering the bias
2. We are lowering the variance
3. We are increasing the bias
4. We are increasing the variance
How many times we need to train our SVM model in such case?
1
2
3
4
Linear Regression is a machine learning algorithm based on _____.
unsupervised learning
supervised learning.
reinforcement learning
none of these
Regression models a target prediction value based on _____.
dependent variable
independent variables
independent value
dependent value
regression technique finds out a linear relationship between x (input) and y(output) hence it is called as _________.
Hypothesis function
Related regression
Linear Regression
none of these
In Linear Regression RMSE stands for_________.
Root Mean Squared Error
Read Mean Squared Error
Root Mode Squared Error
none of these
Root Mean Squared error give difference between_________.
original value and wrong value
predict value and true value
True value and false value
none of these
A decision tree has low training error and a large test error. What is the possible problem?
Decision tree is too shallow
Learning rate too high
There is too much training data
Decision tree is overfitting
Which of the following is a disadvantage of non-parametric machine learning algorithms?
Capable of fitting a large number of functional forms (Flexibility)
Very fast to learn (Speed)
More of a risk to overfit the training data (Overfitting)
They do not require much training data
For Ridge Regression, if the regularization parameter = 0, what does it mean?
Large coefficients are not penalized
Overfitting problems are not accounted for
The loss function is as same as the ordinary least square loss function
All of the above
Which of the following is a disadvantage of non-parametric machine learning algorithms?
Capable of fitting a large number of functional forms (flexibility)
Very fast to learn (speed)
More of a risk to overfit the training data (overfitting)
They do not require much training data
Which of the following is a true statement for regression methods in the case of feature selection?
Ridge regression uses subset selection of features
Lasso regression uses subset selection of features
Both use subset selection of features
None of above
To check the linear relationship of dependent and independent continuous variables, which of the following plots are best suited?
Scatter plot
Bar chart
Histograms
All of the above
Which of the following of the coefficients is added as the penalty term to the loss function in Lasso regression?
Squared magnitude
Absolute value of magnitude
Number of non-zero entries
None of the above
What type of penalty is used on regression weights in Ridge regression?
L0
L1
L2
None of the above
If two variables, x and y, have a very strong linear relationship, then_____
There is evidence that x causes a change in y
There is evidence that y causes a change in x
There might not be any causal relationship between x and y
None of these alternatives is correct
Lasso Regression uses which norm?
L1
L2
L1 & L2 both
None of the above
In Ridge regression, A hyper parameter is used called “_____________” that controls the weighting of the penalty to the loss function.
Alpha
Gamma
Lambda
None of above
Is the logistic regression model a Generalized Linear Model (GLM)? What is a possible reason?
No, it possible the shape function highly logistic
Yes, it's a GLM but only by convention. It's properties don't match with the current definition
Yes, it's a GLM since it's parameterized by a linear combination of its features, and
No, it's not a GLM since it belongs to the 'exponential' family of distributions
Yes, it's a GLM since it's parameterized by a linear combination of its features,
Which of the following is false regarding logistic regression?
We can solve the maximum log-
We can solve the maximum log- likelihood
We can solve the maximum log-
The conditional
A regression model in which more than one independent variable is used to predict the
a simple linear regression model
a multiple regression model
none of the above
A term used to describe the case when the independent variables in a multiple regression
regression
correlation
multicollinearity
none of the above
Which of the following methods do we use to best fit the data in Logistic Regression?
Least Square Error
Maximum Likelihood
Jaccard distance
Both A and B
Which of the following evaluation metrics can not be applied in case of logistic
AUC-ROC
Accuracy
Logloss
Mean-Squared-Error
Which of the following algorithms do we use for Variable Selection?
LASSO
Ridge
Both
None of these
Logistic regression is used to predict valued output?
Continuous
Categorical
Discrete
Ordinal
How many types in logistic regression
4
3
2
43
Logistic regression is when the observed outcome of dependent variable can
Binomial
Multinomial
Ordinal
Discrete
Which of the following is link function in logistic regression __________
Identity
Logit
Error
Logit
The odds of the dependent variable equaling a case (given some linear combination x of the
the linear regression
function of the linear regression
calculations
estimation method
Regression coefficients in logistic regression are estimated using.
Ordinary least squares method
Maximum likelihood estimation method
Dependent variable equalling a case
calculations
Which of the following is analogous to R-Squared for logistic regression.
Likelihood ratio R-squared
McFadden R-squared
Cox and Snell R-Squared
All of the above
