Question Bank - Machine Learning

What is Machine learning?

A) The selective acquisition of knowledge through the use of
computer programs
B) The selective acquisition of knowledge through the use of
manual programs
C) The autonomous acquisition of knowledge through the use
of computer programs
D) The autonomous acquisition of knowledge through the use
of manual programs

What’s the key benefit of using deep learning for tasks like
recognizing images?
A) They need less training data than other methods.
B) They’re easier to explain and understand than other models.
C) They can learn complex details from the data on their own.
D) They work faster and are more efficient computationally.

Which type of machine learning algorithm falls under the

category of “unsupervised learning”?
A) Linear Regression
B) K-means Clustering
C) Decision Trees
D) Random Forest

________ is the application of machine learning.

A) Sentimental analysis
B) Traffic prediction
C) Speech and face recognition
D) All of the above
Which of the following ML algorithms can be used with
unlabelled data?
A) Instance-based algorithms
B) Regression algorithms
C) Clustering algorithm
D) All of the above

Which of the following is not a Machine Learning?

A) Rule-based interference
B) Artificial intelligence
C) Both A and B
D) Neither A nor B

Classification is a category of ____________.

A) Unsupervised Learning
B) Supervised Learning
C) Reinforcement learning
D) Semi-supervised learning

Which of the following learning strategy is appropriate where

the availability of labelled data is partial?
A) Unsupervised Learning
B) Supervised Learning
C) Reinforcement learning
D) Semi-supervised learning

Negative reinforcement refers to _____________.

A) Removes an undesirable stimulus to encourage a desired
behavior
B) Encourages the agent to repeat the behavior
C) Rewards the agent for taking a desired action
D) None of these
Hebbian rule is a supervised lerning rule.
A) TRUE
B) FALSE

Which of the following is not a supervised machine learning

algorithm?
A) K-means
B) Naïve Bayes
C) SVM for classification problems
D) Decision tree

What is the key difference between supervised and

unsupervised learning?
A) Supervised learning requires labeled data, while
unsupervised learning does not.
B) Supervised learning predicts labels, while unsupervised
learning discovers patterns.
C) Supervised learning is used for classification, while
unsupervised learning is used for regression.
D) Supervised learning is always more accurate than
unsupervised learning.

An artificially intelligent car decreases its speed based on its

distance from the car in front of it. Which algorithm is used?
A) Naïve-Bayes
B) Decision Tree
C) Linear Regression
D) Logistic Regression

Which of the following is the main goal of machine learning?

A) Enable computers to learn data
B) To automate manual tasks
C) To make computers intelligent
D) To generate self-aware machines
Deep learning is a subset of _______.
A) Artificial Intelligence
B) Machine Learning
C) Both AI & ML
D) Data Mining

Decision tree algorithm is an example of Supervised ML

algorithm.
A) TRUE
B) FALSE

Apriori Algorithm is an example of Clustering.

A) TRUE
B) FALSE

Trial, error, and delay are the most relevant characteristics of

___________.
A) Unsupervised Learning
B) Supervised Learning
C) Reinforcement learning
D) Semi-supervised learning

Learning rule in ANN refers to a set of instructions or

mathematical formula.
A) TRUE
B) FALSE

In this rule, Δw = αxiy where α is ___________.

A) Weight
B) Bias
C) Learning rate
D) Input vector
Perceptron learning rule is developed by _____________.
A) Donald Hebb
B) John McCarthy
C) Rosenblatt
D) McCulloh

Correlation rule is an unsupervised learning rule.

A) TRUE
B) FALSE

The earliest neural network developed by McCulloch-Pitts in

the year _______.
A) 1949
B) 1934
C) 1943
D) 1945

ADALINE refers to ____________.

A) Adaptive Layer Network
B) Asymmetrical Linear Neural Network
C) Adaptive Linear Neural Network
D) Asymmetrical Ladder Network

Which of the following logic function is a non-linear separable

problem.
A) AND
B) XOR
C) OR
D) NOT
The motive of the delta learning rule is to minimize the error
between ___________ and __________ .
A) Input vector; Output vector
B) Weights; biases
C) Output vector; Target vector
D) None of these

_________ is the connection between the axon and other

neuron dendrites.
A) Axon
B) Soma
C) Synapse
D) Dendrite

ReLU refers to _______________.

A) Rectified Linear Unit
B) Rectified Layer Unit
C) Registered Layer Unit
D) Revised Linear Unit

Recurrent networks are feedback networks with closed loops.

A) TRUE
B) FALSE

Multi-layer Perceptron can be used to distinguish data that is

not linearly separable.
A) TRUE
B) FALSE

Perceptron rule can be applicable in Multi-layer neural netwrok.

A) TRUE
B) FALSE
‘Winner takes it all’ rule refers to _____________.
A) Correlation learning rule
B) Perceptron learning rule
C) Outstar learning rule
D) Competitive learning rule

Perceptron network can be used to solve non-linear separable

problem.
A) TRUE
B) FALSE

Delta rule was developed by ____________.

A) Donald Hebb
B) Rosenblatt
C) McCulloch-Pitts
D) Widrow-Hoff

Which is the cell body of the neuron?

A) Axon
B) Soma
C) Synapse
D) Dendrite

Data preprocessing involves ____________.

A) Cleaning the data
B) Handling missing data
C) Normalizing the data
D) All of the above

Axon is equivalent to ____________ in ANN.

A) Input
B) Output
C) Weight
D) Node
How many hidden layers are present in single layer
feedforward network?
A) One
B) Two
C) Three
D) None of these

GAN stands for _____________.

A) General Adaline Network
B) Generative Allied network
C) Generative Adversarial Network
D) General Adaptive Network

Multi-layer Perceptron are trained using which of the following

algorithm ____________.
A) Widrow-Hoff
B) Gradient-Descent
C) Back Propagation
D) None of these

Which of the following are common classes of problems in

machine learning?
A) Regression
B) Classification
C) Clustering
D) All of the above

Decision tree cannot be used for clustering

A) TRUE
B) FALSE
________ is used as an input to the machine learning model for
training and prediction purposes.
A) Feature
B) Feature vector
C) Both Feature and Feature vector
D) None of the above

Which language is best for ML?

A) C
B) JAVA
C) Python
D) HTML

The term Machine Learning was coined by ___________.

A) James Gosling
B) Arthur Samuel
C) Guido van Rossum
D) None of these

What is called the average squared difference between

classifier predicted output and actual output?
A) Mean realtive error
B) Mean squared error
C) Mean absolute error
D) Root mean squared error

Machine Learning is a field of AI consisting of learning

algorithms that _________.
A) At executing some task
B) Over time with experience
C) Improve their performance
D) All of these
Application of machine learning methods to large databases is
called __________.
A) Data Mining
B) Artificial Intelligence
C) Big Data Computing
D) Internet of Things

The process of adjusting the weight in ANN is known as?

A) Activation
B) Synchronisation
C) Learning
D) None of the above

Which of the following model has ability to learn?

A) Pitts model
B) Rosenblatt perceptron model
C) Both rosenblatt and pitts model
D) Neither rosenblatt nor pitts
The purpose of the Convolutional layer in CNN is to
A) Clean the data
B) Normalize the data
C) Reduce computational complexity
D) Reduce spatial dimension

The backpropagation law is also known as the generalized Delta

rule.
A) TRUE
B) FALSE

Which of the following algorithms are used in ML?

A) Naive Bayes
B) Support Vector Machines
C) K-Nearest Neighbors
D) All of the above
____________ is the scenario when the model fails to decipher
the underlying trend in the input data.
A) Overfitting
B) Underfitting
C) Both overfitting and underfitting
D) None of these

Which of the following problems are grouped under Supervised

learning?
A) Classification
B) Regression
C) Both Classification and Regression
D) None of the above

Which machine learning models are trained to make a series of

decisions based on the rewards and feedback they receive for
their actions?
A) Supervised learning
B) Unsupervised learning
C) Reinforcement learning
D) All of the above

Which of the following is not a supervised learning?

A) PCA
B) Naive Bayesian
C) Linear Regression
D) Decision Tree

Logistic regression is a __________ regression technique that is

used to model data having a __________ outcome.
A) Linear, Binary
B) Linear, NUmeric
C) Nonlinear, Binary
D) Nonlinear, Numeric
If machine learning model output involves target variable then
that model is called as ___________.
A) Descriptive model
B) Predictive model
C) Reinforcement learning
D) All of the above

The procedure to incrementally update each of weights in

neural is referred to as?
A) synchronisation
B) learning law
C) learning algorithm
D) both learning algorithm & law

Delta learning is of unsupervised type?

A) YES
B) NO

Is there a feedback in final stage of backpropagation algorithm?

A) YES
B) NO

Does backpropagaion learning is based on gradient descent

method?
A) YES
B) NO

In biological neural network, signal transmission at synapse is a

_________.
A) Physical process
B) Chemical process
C) Physical & chemical both
D) None of these
Competitive learning net is used for?
A) Pattern grouping
B) Pattern storage
C) Pattern grouping or storage
D) None of these

Mean squared error is a simple and commonly used cost

function.
A) TRUE
B) FALSE

Alisa is beauty in which beauty can be represented by

__________.
A) Fuzzy Set
B) Crisp Set
C) Fuzzy & Crisp Set
D) None of the mentioned

Which of the following are the ways to represent uncertainty?

A) Probability
B) Entropy
C) Fuzzy Logic
D) All of these

The purpose of Softmax function is to adjust the outputs of a

convolutional neural network (CNN) so that they sum to ____.
A) 0
B) 2
C) 1
D) 4
Which activation function is commonly used in the output layer
of binary classification problems?
A) Sigmoid
B) ReLU (Rectified Linear Unit)
C) Tanh (Hyperbolic Tangent)
D) Softmax

Which deep learning model is used for generating realistic

images from random noise?
A) Autoencoder
B) Variational Autoencoder (VAE)
C) GAN (Generative Adversarial Network)
D) Boltzmann Machine

Does McCulloch-pitts model have ability of learning?

A) YES
B) NO

What’s the other name of widrow & hoff learning law?

A) Hebb
B) LMS
C) MMS
D) None of these

What are general limitations of back propagation rule?

A) Local minima problem
B) Slow convergence
C) Scaling
D) All of these

The fundamental unit of neural network is _________.

A) Brain
B) Nucleus
C) Neuron
D) Axon
What is purpose of Axon in BNN?
A) Receptors
B) Transmitter
C) Transmission
D) None of these

Which is the most direct application of neural networks?

A) Vector quantization
B) Pattern mapping
C) Pattern classification
D) Control applications

What is the form of Fuzzy logic?

A) Two-valued logic
B) Crisp set logic
C) Many-valued logic
D) Binary set logic

Fuzzy logic is usually represented as ___________.

A) IF-THEN-ELSE rules
B) IF-THEN rules
C) Both IF-THEN-ELSE rules & IF-THEN rules
D) None of these

__________ function is used in the hidden layers of a neural

network to add non-linearity.
A) Sigmoid
B) ReLU
C) Softmax
D) Identity
In deep learning, what does the term “epoch” refer to?
A) The number of layers in a neural network
B) The process of adjusting learning rates during training
C) The number of iterations over the entire training dataset
during training
D) The technique for initializing the weights of a neural network