wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

ML

Total questions: 48

Worksheet time: 48mins

Name
Class
Date
1.

_________is programming computers to optimize a performance criterion using example data or past experience.

a)

ML

b)

Data science

c)

Big data

d)

Neural network

2.

Which of these doesn't require 'learning'

a)

navigating on Mars

b)

speech recognition

c)

routing on a computer network

d)

user biometrics

e)

calculate payroll

3.

Which of these are the applications of classification in ML

a)

Pattern recognition

b)

Face recognition

c)

Outlier/novelty detection

d)

Medical diagnosis

e)

Character recognition

4.

Examples of unsupervised learning

a)

Customer segmentation in CRM

b)

Image compression: Color quantization

c)

Bioinformatics: Learning motifs

d)

Outlier detection: Credit card Fraud

5.

(a)   predicts the value of the dependent attribute from the attribute variables

6.

Dependent attribute is (a)   for regression

7.

Dependent attribute is _______for classification

a)

Numerical

b)

Alphanumeric

c)

Categorical

d)

Mixed data

8.

Different types of data in a dataset

a)

Transactional Data and Sequence Data

b)

Spatio-Temporal Data

c)

Interval Data and Time Series Data

d)

Spatial Data and Data set with multiple kinds of data

9.

Interpretations of noise

a)

Imprecision in recording the input attributes

b)

Errors in labeling the data points

c)

Additional attributes which were not considered

d)

Unwanted anomaly in the data

10.

Abbreviate PAC

a)

Probably Approximately Correct

b)

Principle Component Analysis

c)

Principle Analysis of Components

11.

______ is the process of choosing one among many candidate models for a predictive modeling problem.

a)

Model Extraction

b)

Model Creation

c)

Model Generalization

d)

Model Selection

12.

There are ______ways to write 'd' binary values in the Model selection and generalization with a binary function

a)

2^2d

b)

2^d

c)

d^n

d)

n^d

13.

______set of assumptions we make to have learning possible

a)

Variance

b)

Bias

c)

Inductive bias

14.

Hypothesis class H is less complex than the function

a)

Good balanced model

b)

Underfitting

c)

Noise

d)

Overfitting

15.

________tries to find the parameter values that maximizes the likelihood function

a)

MLE (Maximum Likelihood Estimation)

b)

Probability Distribution Function

c)

Likelihood Function

d)

Bernoulli Density

16.

Gaussian Distribution / Normal Distribution represent data as a____

a)

Polygon

b)

Bell curve

c)

Straight line

d)

Clusters

17.

_______is a integral of pdf over the range a & b

a)

Probability

b)

Profitability

c)

Counting

18.

Examples of Parametric methods

a)

Regression

b)

LDA

c)

KNN

d)

Simple perceptron

e)

SVM

19.

Disadvantages of Parametric methods

a)

Constrained

b)

Limited Complexity

c)

Poor fit

d)

Overfitting

20.

Examples of Non parametric methods

a)

KNN

b)

Decision Trees

c)

SVM

d)

Naive Bayes

e)

Neural Networks

21.

Disadvantages of non parametric methods

a)

Lots of data

b)

Overfitting

c)

High performance

d)

Lots of features

22.

_______is single global model and ________ is small number of local models

a)

Parametric, Non parametric

b)

Non Parametric, Parametric

c)

Semi Parametric, Parametric

d)

Parametric, Semi Parametric

23.

Case-based or Instance-based distance measures

a)

KNN

b)

Learning Vector Quantization(LVQ)

c)

SVM

d)

Decision Tree

24.

_____represents the shortest distance between two points

a)

Minkowski Distance

b)

Manhattan Distance

c)

Euclidean Distance

d)

Hamming Distance

25.

Find the Euclidean distance between points P(3, 2) and Q(4, 1).

a)

PQ = √2 unit.

b)

PQ = 2 unit.

c)

PQ = √3 unit.

d)

PQ = √4 unit.

26.

Find manhattan distance of

row1 = [10, 20, 15, 10, 5]

row2 = [12, 24, 18, 8, 7]

a)

12

b)

14

c)

13

d)

15

27.

Hamming distance of

String 1 = 1V1A0R6U0NS9

String 2 = 1A1B0H6ILASH

a)

7

b)

7+1

c)

5

d)

6

28.

This formula is used to evaluate_____

a)

Hamming Distance

b)

Minkowski Distance

c)

Manhattan Distance

d)

Bernoulli Density

29.

____model parameters actually grow with the training data set

a)

KNN

b)

SVM

c)

NAIVE BAYES

d)

RANDOM FOREST

30.

Chooses subset of the original set

a)

Feature selection

b)

Feature Extraction

c)

Feature Creation

d)

LDA

31.

PCA is ____________

a)

Dimensionality Reduction

b)

Standardizing the data

c)

Computing the Covariance

d)

Multiclass Classifier

32.

The number of instances that were positive (+) and incorrectly classified as negative (-)

a)

Type 2 Error

b)

Type 1 Error.

c)

False Negative

d)

True Positive

33.

A measure of the variance that a factor explains for observed variables.

a)

Eigen vector

b)

Eigen value

c)

Principle component

d)

Factor

34.

in _______ data is stretched, rotated and translated

a)

Factor Analysis

b)

PCA

c)

LDA

d)

PAC

35.

_____centers the data at the origin and rotates the axes

a)

PCA

b)

LDA

c)

Factor Analysis

d)

PAC

36.

Difference between truth value of parameters and mean value of the estimator is ____

a)

Bias of the parameter

b)

Bias of the estimator

c)

Variance of the parameter

d)

Bias of the parameter

37.

Model with low bais and low variance is ___

a)

Good model

b)

Balanced model

c)

Overfitting

d)

Underfitting

38.

Distance from the discriminant to the closest instances on either side

a)

Boundary

b)

Margin

c)

Hyper plane

d)

Support vector

39.

SVM algorithm creates the best line or ________

a)

Decision boundary

b)

Hyperplane

c)

Support vector

d)

Margin

40.

This best decision boundary is called a ______.

a)

Margin

b)

Support vector

c)

Hyperplane

d)

SVM

41.

_________is a method of using linear classifier to solve a non-linear problem

a)

Kernel trick

b)

Kernel function

c)

Kernel bias

d)

Kernel machines

42.

__________activation function takes a value as input and outputs another value between 0 and 1

a)

Recurrent

b)

Tanh

c)

relu

d)

Sigmoid

43.

In BPN minimum value of the error function in weight space is done by _____

a)

PCA

b)

Factor Analysis

c)

Gradient descent.

d)

LDA

44.

Calculate h1

a)

0.2775

b)

1.2775

c)

1.3755

d)

0.3775

45.

Which of these is not an element of Reinforcement learning?

a)

Environment

b)

Policy

c)

Reward

d)

Action

e)

Sarsa

46.

Global Approach - Learner fusion

a)

Voting and Stacking

b)

Voting and Gating model

c)

Cascading

d)

Voting and Cascading

47.

Generating a sequence of base learners each focusing on the previous one's errors

a)

AdaBoost

b)

Bagging

c)

Voting

d)

Cascading

48.

Multistage Combination methods

Uses serial approach

a)

Cascading

b)

Stacking

c)

Voting

d)

Boosting