Font size
WorksheetsAI QUIZ
Total questions: 100
Worksheet time: 2hrs 40mins
Identify the Problem:
We have Information of all previous general elections with respect to party, votes, Candidates, Locality, Issues in nation, etc. With All this information we need to find the winner of next general election.
Classification
Regression
Clustering
none of them
Identify the problem:
We have information of all houses in a particular area like size, type and design of house, locality, colour, previous purchase etc. on the basis of these data we have to find the price of a particular house.
Classification
Regression
Clustering
Prbabilistic
Identify a problem:
You have details of corona affected positive cases found in various regions. Depending upon parameters like number of increasing corona infected patients, weather conditions etc. regions are classified into red zone, Green zone and Orange Zone. On the basis of these data we have to predict the region of a city.
classification
regression
clustering
unsupervised learning
State whether True or False
The most meaningful and interpretable principal components are those that have the largest eigenvalues
True
False
Cross validation is used for
Comparing predictors
Selecting parameters in prediction function
Selecting variables to include in a model
All of the mentioned
State True or False
For k cross-validation, larger k value implies more bias.
True
False
which of the following is not a method of cross validation?
Leave One Out CV
K-Fold CV
Stratified K-Fold CV
Timeline CV
If I am using all features of my dataset and I achieve 100% accuracy on my training set, but ~70% on validation set, what should I look out for?
Overfitting
Underfitting
Bestfitting
Give the correct Answer for following statements.
1. It is important to perform feature normalization before using the Gaussian kernel.
2. The maximum value of the Gaussian kernel (i.e., ) is 1.
Statement 1 is True and 2 is False
Statement 1 is False and 2 is True
Both statements are False
Both Statements are True
Which is/are method to do multiclass classification?
One Vs Rest
One vs One
All vs One
One vs Other
Following is Linear SVM classifier with 2 class classification problem. Now you have been given the following data in which some points are circled red that are representing support vectors.
If you remove the following any one red points from the data. Will the decision boundary change?
True
False
Suppose you are dealing with 4 class classification problem and you want to train a SVM model on the data for that you are using One-vs-all method. Now, say for training 1 time in one vs all setting the SVM is taking 10 second. How many seconds would it require to train one-vs-all method end to end?
20
40
80
60
For evaluating regression models, which of the following metrics can not be used ?
R Squared
Adjusted R Squared
SSE
MST
Suppose that we have N independent variables (X1,X2… Xn) and dependent variable is Y. Now Imagine that you are applying linear regression.You found that correlation coefficient for one of it’s variable(Say X1) with Y is -0.95.
Which of the following is true for X1?
Relation between the X1 and Y is weak
Relation between the X1 and Y is strong
Relation between the X1 and Y is nutral
Correlation can’t judge the relationship
Suppose that you have a dataset D1 and you design a linear regression model of degree 3 polynomial and you found that the training and testing error is “0” or in another terms it perfectly fits the data.
What will happen when you fit degree 4 polynomial in linear regression?
There are high chances that degree 4 polynomial will over fit the data
There are high chances that degree 4 polynomial will under fit the data
Can't Predict
None of these
Which of the following function is used by Logistic Regression to convert the probability in between [0,1]
Sigmoid
polynomial
square
rbf
Regarding Bias and Variance ,which of the following statement is True?
Model which overfit has high bias and high variance
Model which overfits have Low bias and low variance
Model which overfits has high Bias and Low variance
Model which overfits has low Bias and High Variance
Which of the following is true about Lasso and Ridge Regression?
Ridge regression uses subset selection of features
Lasso regression uses subset selection of features
Both uses subset selection of features
None of them are used for subset selection of features
Identify Performance measure P from following Traffic Pattern Analysis Algorithm.
Predict traffic patterns at a busy intersection
Tune Model with data about past traffic patterns
Predict future traffic patterns
None of the above
Select All prime reasons for using unsupervised Machine Learning Algorithms.
Finds all kind of unknown patterns in data.
Help you to find features which can be useful for categorization.
Help you to Predict whether a fruit is apple or not
Help you to predict prize of stock
Consider the above Confusion Matrix of a classifier and choose the correct statements
Accuracy is 84%
Misclassification Rate is 16%
Type-I Error is 6
Type-II Error is 10
What is Machine learning?
The autonomous acquisition of knowledge through the use of computer programs
he autonomous acquisition of knowledge through the use of manual programs
The selective acquisition of knowledge through the use of computer programs
The selective acquisition of knowledge through the use of manual programs
__________________ algorithms enable the computers to learn from data, and even improve themselves, without being explicitly programmed.
Artificial Intelligence
Machine Learning
Deep Learning
Traditional Learning
What device below is not an example of Machine Learning?
Wearable fitness tracker
Google Assistant
Speech to Text
Google Search
None of the above
_______________________ is a category of an algorithm that allows software applications to become more accurate in predicting outcomes without being explicitly programmed.
Artificial Intelligence
Machine Learning
Deep Learning
Traditional Learning
Who is the Chess grand master beaten in a game by I.B.M.'s system?
Gary Kapov
Garry Kasper
Gary Kasparov
Gary Kerpov
What are the three types of Machine Learning? Choose three.
Supervised Learning
Learning Differentiated
Unsupervised Learning
Reinforcement Learning
Technical Learning
What are the two types of Supervised Learning?
Classification
Declassification
Progression
Regression
What are the two types of Unsupervised Learning?
Loitering
Clustering
Association
Dissociation
In this type of Machine Learning, an AI system is presented with unlabeled, uncategorized data and the system’s algorithms act on the data without prior training. The output is dependent upon the coded algorithms.
Supervised Learning
Unsupervised Learning
Reinforcement Learning
Technique Learning
Tom Mitchell of Carnegie Mellon University said that, "A computer program is said to learn from experience E with respect to some "T" and some performance measure P, if its performance on T, as measured by P, improves with experience E." What is "T"?
Time
Test
Task
Temper
What is Machine Learning? (Choose 3 Answers)
Artificial Intelligence
Machine Learning
Data Statistics
Deep Learning
What kind of learning algorithm for "Future stock prices or currency exchange rates"?
Recognizing Anomalies
Prediction
Generating Patterns
Recognition Patterns
Which of the following is not type of learning?
Semi-unsupervised Learning
Unsupervised Learning
Supervised Learning
Reinforcement Learning
This picture shows an application of ...
Supervised Learning: Classification
Unsupervised Learning: Clustering
Unsupervised Learning: Prediction
Supervised Learning: Regression
Field of study that gives computers the ability to learn without being explicitly programmed.
Deep Learning
Machine Learning
Data Science
What would make a robot intelligent?
It responds to the environment.
It responds to the environment according to previous experiences.
It calculates mathematical problems faster than human minds.
It can jump 1.5 meters higher than humans.
A major benefit of an machine with AI is
it could do a job too dangerous for a human
it could love you like a brother
it could chop up your vegetables
A major benefit of an machine with AI is
it could do a job too dangerous for a human
it could love you like a brother
it could chop up your vegetables
A major benefit of an machine with AI is
it could do a job too dangerous for a human
it could love you like a brother
it could chop up your vegetables
A major benefit of an machine with AI is
it could do a job too dangerous for a human
it could love you like a brother
it could chop up your vegetables
What would make a robot intelligent?
It responds to the environment.
It responds to the environment according to previous experiences.
It calculates mathematical problems faster than human minds.
It can jump 1.5 meters higher than humans.
A major benefit of an machine with AI is
it could do a job too dangerous for a human
it could love you like a brother
it could chop up your vegetables
What is Machine Learning? (Choose 3 Answers)
Artificial Intelligence
Machine Learning
Data Statistics
Deep Learning
What kind of learning algorithm for "Future stock prices or currency exchange rates"?
Recognizing Anomalies
Prediction
Generating Patterns
Recognition Patterns
What kind of learning algorithm for "Facial identities or facial expressions"?
Recognizing Anomalies
Prediction
Generating Patterns
Recognition Patterns
Which of the following is not type of learning?
Semi-unsupervised Learning
Unsupervised Learning
Supervised Learning
Reinforcement Learning
This picture shows an application of ...
Supervised Learning: Classification
Unsupervised Learning: Clustering
Unsupervised Learning: Prediction
Supervised Learning: Regression
Field of study that gives computers the ability to learn without being explicitly programmed.
Deep Learning
Machine Learning
Data Science
What is Machine learning?
The autonomous acquisition of knowledge through the use of computer programs
The autonomous acquisition of knowledge through the use of manual programs
The selective acquisition of knowledge through the use of computer programs
The selective acquisition of knowledge through the use of manual programs
Different learning methods does not include?
Memorization
Analogy
Deduction
Introduction
Machine Learning is a branch of..
AI
Java
c
c++
ANN is related to ...
ML
AI
Deep Learning
Java
____is responsible for 2D structures
Numpy
panda
matplotlib
sklearn
The equation of line is ...
y=mx+c
m=ab+cf
p=ann
AI=DL+ML
The most widely used metrics and tools to assess a classification model are:
Confusion matrix
Cost-sensitive accuracy
Area under the ROC curve
All of the above - answer
A computer system can use it to perform a task without using instructions from us, relying on patterns and inference instead.
Algorithm
Machine Learning
Deep Learning
Neural Network
What would make a robot intelligent?
It responds to the environment.
It calculates mathematical problems faster than human minds.
It responds to the environment according to previous experiences.
It can jump 2 meters higher than humans.
Type of machine learning algorithm used to infer information from data without input from humans. In other words, learning without a teacher.
Dataset
Supervised learning
Unsupervised learning
Classifiers
All data is labeled and the algorithms learn to predict the output from the input data. In other words, giving concrete known examples to the computer.
Dataset
Supervised learning
Unsupervised learning
Classifiers
In a classification problem, the outputs are
categorical or discrete
numerical or continuous
In a regression problem, the outputs are
categorical or discrete
numerical or continuous
The data is split according to a certain requirements
Sentiment analysis
Reinforcement learning
Decision tree learning
Predictive models
To identify and categorize opinions in text, in order to work out if the writer's attitude is positive, negative, or neutral.
Predictive model
Reinforcement learning
Sentiment analysis
Decision tree learning
To validate a model, you use the (a) dataset.
In visualization shown above, fit of three different models (in blue line) on same training data. What can you conclude from these visualizations?
1) The training error in first model is higher when compared to second and third model.
2) The best model for this regression problem is the last (third) model, because it has minimum training error.
3) The second model is more robust than first and third because it will perform better on unseen data.
4) The third model is overfitting data as compared to first and second model.
5) All models will perform same because we have not seen the test data.
1 and 3
1 and 2
1, 3 and 4
Only 5
The Goal of model tuning is to find a model _______
That is at least 95% accurate on the training data set
That takes less than 30 minutes to train and validate
That makes you feel like you are a true machine learning expert
That is at the sweet spot between a simple working model and a very complex one
The Ideal model have : ….. (you may select multiple answers)
Low variance
High variance
Low bias
High bias
A collection of individual models that learn to predict a target by combining their strengths and avoiding the weaknesses of each is called ________
A Collection
An Ensemble
A Group
A Fusion
Which among the below options are types of Feature engineering? (May choose multiple answers)
Replacing missing value
Getting mean value from a group of entities
Extracting city from home address
Changing hyper-parameter values
Confusion matrix gives you a more complete picture of how your classifier is performing.
Compute the following from the confusion matrix: Accuracy
87.54
92.12
90.90
91.16
Compute the following from the confusion matrix: Sensitivity
95.23
91.78
85.91
87.51
Compute the following from the confusion matrix: Specificity
81.52
83.89
82.78
83.33
Compute the following from the confusion matrix: Precision
90.90
91.86
91.87
93.42
Compute the following from the confusion matrix: F-measure
92.97
92.48
91.85
93.02
How do you reduce both types I and II errors from occurring?
It can't be reduced
Increase the sample size
Redo the tests
Tamper with the data
If you use data 1990-2013 to fit the model and then you forecast for 2011-2013, it's _________ prediction. But if you only use 1990-2010 for fitting the model and then you predict 2011-2013, then its __________ prediction.
out-of-sample, in-sample
in-sample, out-of-sample
time series sample, test sample
training sample, out-of-range sample
______ is the process of identifying unexpected items in datasets, which differ from the norm.
Reinforcement learning
Classification
Clustering
Anomaly detection
According to Tom Mitchell, what is the requirement for the computer system to learn
Data set
Task
Performance measure
Knowledge
Machine learning is mostly used when
Human expertise doesn't exist
Model must be customised to personal need
Model use huge amount of data
Interpreting the insight from descriptive data such as mean, median etc
Select a possible application of the machine learning
Fraud detection
Recognising a happy face
Differentiate X-ray image
Recognise your lecturer's hand writing
To recognise the face as an object, the image of face is breakdown into combination of edges, edges, and pixel.
True
False
What is the implication of "false positive" increase to the precision measure
increase precision
decrease precision
doesn't has any effect to precision
What is the implication of decreasing "false negative" to the recall measure
decreasing recall
increasing recall
doesn't have any effect to recall
In the case of pregnancy prediction, if the predictor output is always "pregnant" what is the recall value?
1
0
0.1
Undefined
In the case of pregnancy prediction, if the predictor output is always "not pregnant" what is the precision value?
1
0
0.5
Undefined
The unsupervised learning is better used for prediction
True
False
Artificial neural network consists of following fundamental components
Neurons as nodes
Synapses as weight
Neurons as weight
Synapses as nodes
Supervised learning used rewards, training data, and desired output
True
False
Suppose your email program watches which emails you do or do not mark as spam, and based on that learns how to better filter spam. What is the task T in this setting?
Classifying emails as spam or not spam
Watching you label emails as spam or not spam
The number of emails correctly classified as spam/not spam
None of the above
You are running a company and you want to develop learning algorithms to address each of two problems.
Problems 1: you have a large inventory of identical items. you want to predict how many of these items will sell over the next 3 months.
Problem 2: you would like software to examine individual customer accounts and for each account decide if it has been hacked/compromised.
Should you treat these as classification or as regression problems?
Treat both as classification problems
Treat problem 1 as classification and problem 2 as regression
Treat problem 1 as regression and problem 2 as classification
Treat both as regression problems
Of the following examples, which would you address using an unsupervised learning algorithm? check all that apply
Given email labeled as spam/not spam, learn a spam filter
Given a set of news articles found on the web, group them into set of articles about the same story
Given a database of customer data, automatically discover market segments and group customers into different market segments
Given a dataset of patients diagnosed as either having diabetes or not, learn to classify new patients as having diabetes or not
In the "model representation", Andrew Ng uses variable "m" to represent
number of training example
input variable
output variable
feature
Which keyword is used to define a function in Python?
def
function
define
func
Which of these is better suited to be solved using regression?
The price of a house based on its area and distance from metro
Whether a house is closer than 5Kms based on its price and area.
What is the primary goal of using a confusion matrix in classification problems?
To determine the feature importance
To calculate the accuracy of a model
To optimize hyperparameters
To visualize the performance of a model
What is the primary goal of reinforcement learning?
To group similar data points
To maximize cumulative reward
To predict future outcomes
To classify data into categories
