Practice objective questions
for quick revision and examination
preparation. Try answering each question
before revealing the answer.
π Neural Networks and Deep Learning
π Unit 1
π― MCQs
Neural Networks and Deep Learning - Unit-1
1
What is purpose of Axon?
Areceptors
Btransmitter
Ctransmission
Dnone of the mentioned
Correct Answertransmission
2
When the cell is said to be fired?
Aif potential of body reaches a steady threshold values
Bif there is impulse reaction
Cduring upbeat of heart
Dnone of the mentioned
Correct Answerif potential of body reaches a steady threshold values
3
The amount of output of one unit received by another unit depends on what?
Aoutput unit
Binput unit
Cactivation value
Dweight
Correct Answerweight
4
The process of adjusting the weight is known as?
Aactivation
Bsynchronisation
Clearning
Dnone of the mentioned
Correct Answerlearning
5
What is adaline in neural networks?
Aadaptive linear element
Bautomatic linear element
Cadaptive line element
Dnone of the mentioned
Correct Answeradaptive linear element
6
In adaline model what is the relation between output & activation value(x)?
Alinear
Bnonlinear
Ccan be either linear or non-linear
Dnone of the mentioned
Correct Answerlinear
7
what is the another name of weight update rule in adaline model based on its functionality?
ALMS error learning law
Bgradient descent algorithm
Cboth LMS error & gradient descent learning law
Dnone of the mentioned
Correct AnswerLMS error learning law
8
State whether Hebbβs law is supervised learning or of unsupervised type?
Asupervised
Bunsupervised
Ceither supervised or unsupervised
Dcan be both supervised & unsupervised
Correct Answerunsupervised
9
Learning is a?
Aslow process
Bfast process
Ccan be slow or fast in general
Dcan't say
Correct Answerslow process
10
What is supervised learning?
Aweight adjustment based on deviation of desired output from actual output
Bweight adjustment based on desired output only
Cweight adjustment based on actual output only
Dnone of the mentioned
Correct Answerweight adjustment based on deviation of desired output from actual output
11
What is unsupervised learning?
Aweight adjustment based on deviation of desired output from actual output
Bweight adjustment based on desired output only
Cweight adjustment based on local information available to weights
Dnone of the mentioned
Correct Answerweight adjustment based on local information available to weights
12
What is the objective of backpropagation algorithm?
Ato develop learning algorithm for multilayer feedforward neural network
Bto develop learning algorithm for single layer feedforward neural network
Cto develop learning algorithm for multilayer feedforward neural network, so that network can be trained to capture the mapping implicitly
Dnone of the mentioned
Correct Answerto develop learning algorithm for multilayer feedforward neural network, so that network can be trained to capture the mapping implicitly
13
What is true regarding backpropagation rule?
Ait is also called generalized delta rule
Berror in output is propagated backwards only to determine weight updates
Cthere is no feedback of signal at nay stage
Dall of the mentioned
Correct Answerall of the mentioned
14
What are general limitations of back propagation rule?
Alocal minima problem
Bslow convergence
Cscaling
Dall of the mentioned
Correct Answerall of the mentioned
15
Does backpropagaion learning is based on gradient descent along error surface?
Ayes
Bno
Ccannot be said
Dit depends on gradient descent but not error surface
Correct Answeryes
16
How can learning process be stopped in backpropagation rule?
Athere is convergence involved
Bno heuristic criteria exist
Con basis of average gradient value
Dnone of the mentioned
Correct Answeron basis of average gradient value
17
What is the objective of associative memories?
Ato store patters
Bto recall patterns
Cto store association between patterns
Dto store association between patterns for later recall of one of patterns given the other
Correct Answerto store association between patterns for later recall of one of patterns given the other
18
What is objective of linear autoassociative feedforward networks?
Ato associate a given pattern with itself
Bto associate a given pattern with others
Cto associate output with input
Dnone of the mentioned
Correct Answerto associate a given pattern with itself
19
What is the objective of a pattern storage task in a network?
Ato store a given set of patterns
Bto recall a give set of patterns
Cboth to store and recall
Dnone of the mentioned
Correct Answerboth to store and recall
20
If the weight matrix stores the given patterns, then the network becomes?
Aautoassoiative memory
Bheteroassociative memory
Cmultidirectional assocative memory
Dtemporal associative memory
Correct Answerautoassoiative memory
21
If the weight matrix stores association between a pair of patterns, then network becomes?
Aautoassoiative memory
Bheteroassociative memory
Cmultidirectional assocative memory
Dtemporal associative memory
Correct Answerheteroassociative memory
22
What is the objective of BAM?
Ato store pattern pairs
Bto recall pattern pairs
Cto store a set of pattern pairs and they can be recalled by giving either of pattern as input
Dnone of the mentioned
Correct Answerto store a set of pattern pairs and they can be recalled by giving either of pattern as input
23
The junctions that allow signal transmission between the axons terminals and dendrites are called ______________
Correct Answersynapses
24
In Neural Networks learning processes, Learning with a teacher is also referred to as _________ learning
Correct Answersupervised
25
___________ Learning is a feedback-based Network technique in which an agent learns to behave in an environment by performing the actions and seeing the results of actions.
Correct AnswerReinforcement
26
The __________ is used to control the amount of weight adjustment at each step of training.
Correct Answerlearning rate
27
The weight updating in case of perceptron learning, if yβ t is _______________
Correct Answerwi(new) = wi(old)+Ξ±txi
28
Madaline stands for ________________
Correct AnswerMultiple Adaptive Linear Neuron
29
In Adaline learning rule is found to minimize the _________ error between the activation and the target value.
Correct Answerleast mean square (LMS)
30
The training of the Back Propagation Network is done in ___________ stages
Correct Answerthree
31
CAM stands for ________________
Correct AnswerContent Addressable Memories
32
In the _________ associative memory network, the training input vector and training output vector are the same.
Correct Answerauto
33
The BAM is a __________ associative pattern-marching network that encodes binary or bipolar patterns using Hebbian learning rule