27 + Interview Questions in Competitive Learning Neural Networks in Neural Networks Page 1 InterviewSolution

1.	What is true regarding adaline learning algorithm(a) uses gradient descent to determine the weight vector that leads to minimal error(b) error is defined as MSE between neurons net input and its desired output(c) this technique allows incremental learning(d) all of the mentionedThis question was addressed to me during an online interview.My doubt stems from Analysis of Feature Mapping Network in division Competitive Learning Neural Networks of Neural Networks
Answer» Right answer is (d) all of the mentioned Best explanation: Incremental learning means REFINING of the weights as more TRAINING samples are ADDED, rest are basic statements that DEFINES ADALINE learning.

Discussion

2.	Use of nonlinear units in the feedback layer of competitive network leads to concept of?(a) feature mapping(b) pattern storage(c) pattern classification(d) none of the mentionedI have been asked this question during an online interview.Query is from Analysis of Feature Mapping Network in chapter Competitive Learning Neural Networks of Neural Networks
Answer» Correct choice is (d) NONE of the mentioned The EXPLANATION: Use of nonlinear units in the feedback LAYER of competitive network leads to concept of PATTERN CLUSTERING.

Discussion

3.	In self organizing network, how is layer connected to output layer?(a) some are connected(b) all are one to one connected(c) each input unit is connected to each output unit(d) none of the mentionedThis question was posed to me during an interview for a job.My query is from Analysis of Feature Mapping Network topic in chapter Competitive Learning Neural Networks of Neural Networks
Answer» Right answer is (c) each input UNIT is CONNECTED to each OUTPUT unit Easy EXPLANATION: In self ORGANIZING network, each input unit is connected to each output unit.

Discussion

4.	What is true for competitive learning?(a) nodes compete for inputs(b) process leads to most efficient neural representation of input space(c) typical for unsupervised learning(d) all of the mentionedThis question was addressed to me in an online interview.My query is from Analysis of Feature Mapping Network topic in section Competitive Learning Neural Networks of Neural Networks
Answer» CORRECT option is (d) all of the mentioned To explain I WOULD SAY: These all STATEMENTS defines the COMPETITIVE learning.

Discussion

5.	In feature maps, when weights are updated forwinning unit and its neighbour, which type learning it is known as?(a) karnaugt learning(b) boltzman learning(c) kohonen’s learning(d) none of the mentionedI got this question in exam.I would like to ask this question from Analysis of Feature Mapping Network topic in division Competitive Learning Neural Networks of Neural Networks
Answer» Right ANSWER is (c) kohonen’s learning Easiest EXPLANATION: Self ORGANIZATION NETWORK is also KNOWN as Kohonen learning.

Discussion

6.	How are weights updated in feature maps?(a) updated for winning unit only(b) updated for neighbours of winner only(c) updated for winning unit and its neighbours(d) none of the mentionedI got this question in class test.I'm obligated to ask this question of Analysis of Feature Mapping Network topic in chapter Competitive Learning Neural Networks of Neural Networks
Answer» The CORRECT option is (c) updated for winning UNIT and its NEIGHBOURS To explain: Weights are updated in feature maps forwinning unit and its neighbours.

Discussion

7.	What kind of learning is involved in pattern clustering task?(a) supervised(b) unsupervised(c) learning with critic(d) none of the mentionedThe question was posed to me during an interview for a job.My question is taken from Analysis of Feature Mapping Network topic in division Competitive Learning Neural Networks of Neural Networks
Answer» The correct choice is (B) unsupervised Best explanation: SINCE pattern CLASSES are FORMED on unlabelled classes.

Discussion

8.	How is feature mapping network distinct from competitive learning network?(a) geometrical arrangement(b) significance attached to neighbouring units(c) nonlinear units(d) none of the mentionedThe question was asked in an interview for job.The question is from Analysis of Feature Mapping Network in division Competitive Learning Neural Networks of Neural Networks
Answer» RIGHT answer is (d) NONE of the mentioned To explain I would say: Both the geometrical arrangement and significance ATTACHED to neighbouring UNITS make it distinct.

Discussion

9.	What is the objective of feature maps?(a) to capture the features in space of input patterns(b) to capture just the input patterns(c) update weights(d) to capture output patternsThis question was posed to me in unit test.I want to ask this question from Analysis of Feature Mapping Network in chapter Competitive Learning Neural Networks of Neural Networks
Answer» RIGHT option is (a) to capture the features in space of INPUT patterns The BEST I can explain: The OBJECTIVE of FEATURE maps is to capture the features in space of input patterns.

Discussion

10.	In competitive learning, node with highest activation is the winner, is it true?(a) yes(b) noThis question was addressed to me by my college professor while I was bunking the class.Enquiry is from Feedback Layer in section Competitive Learning Neural Networks of Neural Networks
Answer» RIGHT OPTION is (a) yes For EXPLANATION: This itself DEFINES the competitive LEARNING.

Discussion

11.	Generally how many kinds of pattern storage network exist?(a) 2(b) 3(c) 4(d) 5The question was posed to me in class test.I'd like to ask this question from Feedback Layer topic in chapter Competitive Learning Neural Networks of Neural Networks
Answer» Correct choice is (B) 3 Best explanation: NAMELY, TEMPORARY STORAGE, Short term memory, LONG term memory.

Discussion

12.	what kind of feedbacks are given in competitive layer?(a) self excitatory to self and others(b) inhibitory to self and others(c) self excitatory to self and inhibitory to others(d) inhibitory to self and excitatory to othersThe question was asked in an online quiz.This intriguing question originated from Feedback Layer topic in section Competitive Learning Neural Networks of Neural Networks
Answer» RIGHT choice is (C) SELF excitatory to self and inhibitory to others Easiest explanation: The second layer of competitive networks haveself excitatory to self and inhibitory to others feedbacks to MAKE it competitive.

Discussion

13.	What is the other name of feedback layer in competitive neural networks?(a) feedback layer(b) feed layer(c) competitive layer(d) no such name existThe question was asked in a national level competition.I'd like to ask this question from Feedback Layer topic in division Competitive Learning Neural Networks of Neural Networks
Answer» Correct option is (c) competitive LAYER The best I can explain: FEEDBACK layer in competitive NEURAL NETWORKS is also known as competitive layer.

Discussion

14.	What is ojas rule?(a) finds a unit weight vector(b) maximises the mean squared output(c) minimises the mean squared output(d) none of the mentionedI got this question during an interview for a job.The query is from Feedback Layer in chapter Competitive Learning Neural Networks of Neural Networks
Answer» The correct option is (d) none of the mentioned The best explanation: OJAS rule finds a unit weight VECTOR and maximises the mean SQUARED OUTPUT.

Discussion

15.	By normalizing the weight at every stage can we prevent divergence?(a) yes(b) noThis question was addressed to me in unit test.I would like to ask this question from Feedback Layer topic in portion Competitive Learning Neural Networks of Neural Networks
Answer» CORRECT choice is (a) yes The BEST I can EXPLAIN: \|\|w\|\| = 1 .

Discussion

16.	How can divergence be prevented?(a) using hopfield criteria(b) sangers rule(c) ojas rule(d) sangers or ojas ruleThis question was posed to me in exam.The question is from Feedback Layer topic in section Competitive Learning Neural Networks of Neural Networks
Answer» The correct answer is (d) SANGERS or ojas rule For EXPLANATION: Divergence can be PREVENTED by using sangers or ojas rule.

Discussion

17.	What is the natureof weights in plain hebbian learning?(a) convergent(b) divergent(c) may be convergent or divergent(d) none of the mentionedThis question was posed to me during an interview.The origin of the question is Feedback Layer topic in chapter Competitive Learning Neural Networks of Neural Networks
Answer» Right CHOICE is (b) divergent Easiest explanation: In PLAIN hebbian LEARNING weights keep GROWING without bound.

Discussion

18.	The weight change inplain hebbian learning is?(a) 0(b) 1(c) 0 or 1(d) none of the mentionedThis question was posed to me in a job interview.I'm obligated to ask this question of Feedback Layer in division Competitive Learning Neural Networks of Neural Networks
Answer» CORRECT OPTION is (d) none of the mentioned For explanation I would SAY: The weight change inplain hebbian LEARNING can never be zero.

Discussion

19.	An instar can respond to a set of input vectors even if its not trained to capture the behaviour of the set?(a) yes(b) noThe question was posed to me at a job interview.My doubt stems from Feedback Layer in section Competitive Learning Neural Networks of Neural Networks
Answer» The correct choice is (a) yes To elaborate: An instar can RESPOND to a set of input vectors even if it is TRAINED to capture the AVERAGE BEHAVIOUR of the set.

Discussion

20.	How is weight vector adjusted in basic competitive learning?(a) such that it moves towards the input vector(b) such that it movesaway from input vector(c) such that it moves towards the output vector(d) such that it movesaway from output vectorThis question was posed to me in an interview for job.My question is from Competitive Learning Neural Nework Introduction topic in section Competitive Learning Neural Networks of Neural Networks
Answer» Right option is (a) such that it moves towards the INPUT vector The EXPLANATION: Weight vector is ADJUSTED such that it moves towards the input vector.

Discussion

21.	What is an instar?(a) receives inputs from all others(b) gives output to all others(c) may receive or give input or output to others(d) none of the mentionedI have been asked this question during an interview for a job.My doubt stems from Competitive Learning Neural Nework Introduction in portion Competitive Learning Neural Networks of Neural Networks
Answer» The correct ANSWER is (a) RECEIVES inputs from all others For explanation: An instar receives inputs from all other INPUT units.

Discussion

22.	If a competitive network can perform feature mapping then what is that network can be called?(a) self excitatory(b) self inhibitory(c) self organization(d) none of the mentionedThis question was addressed to me during an interview.My question is based upon Competitive Learning Neural Nework Introduction topic in section Competitive Learning Neural Networks of Neural Networks
Answer» Correct OPTION is (c) self organization For explanation I would SAY: COMPETITIVE network that can perform FEATURE mapping can be CALLED as self organization network.

Discussion

23.	What conditions are must for competitive network to perform feature mapping?(a) non linear output layers(b) connection to neighbours is excitatory and tothe farther units inhibitory(c) on centre off surround connections(d) none of the mentioned fulfils the whole criteriaThe question was posed to me in an international level competition.I would like to ask this question from Competitive Learning Neural Nework Introduction topic in portion Competitive Learning Neural Networks of Neural Networks
Answer» The CORRECT choice is (d) NONE of the mentioned fulfils the whole criteria The EXPLANATION is: If cndition in a, b, C are met then feature mapping canbe performed.

Discussion

24.	What conditions are must for competitive network to perform pattern clustering?(a) non linear output layers(b) connection to neighbours is excitatory and tothe farther units inhibitory(c) on centre off surround connections(d) none of the mentioned fulfils the whole criteriaThe question was posed to me in homework.This interesting question is from Competitive Learning Neural Nework Introduction in division Competitive Learning Neural Networks of Neural Networks
Answer» RIGHT CHOICE is (d) none of the mentioned fulfils the whole criteria For EXPLANATION: If the output functions of units in feedback laye are made non-linear , with FIXED weight on-centre off-surround CONNECTIONS, the pattern clustering can be performed.

Discussion

25.	What is the nature of general feedback given in competitive neural networks?(a) self excitatory(b) self inhibitory(c) self excitatory or self inhibitory(d) none of the mentionedI had been asked this question by my school teacher while I was bunking the class.Origin of the question is Competitive Learning Neural Nework Introduction in chapter Competitive Learning Neural Networks of Neural Networks
Answer» The correct answer is (a) self excitatory To EXPLAIN I would SAY: The OUTPUT of each unit in SECOND LAYER is fed back to itself in self – excitatory manner.

Discussion

26.	Which layer has feedback weights in competitive neural networks?(a) input layer(b) second layer(c) both input and second layer(d) none of the mentionedI had been asked this question at a job interview.This interesting question is from Competitive Learning Neural Nework Introduction topic in section Competitive Learning Neural Networks of Neural Networks
Answer» Correct ANSWER is (b) second LAYER To explain I WOULD SAY: Second layer has weights which gives feedback to the layer itself.

Discussion

27.	How are input layer units connected to second layer in competitive learning networks?(a) feedforward manner(b) feedback manner(c) feedforward and feedback(d) feedforward or feedbackI got this question during an online exam.This is a very interesting question from Competitive Learning Neural Nework Introduction in chapter Competitive Learning Neural Networks of Neural Networks
Answer» CORRECT ANSWER is (a) feedforward manner Explanation: The OUTPUT of INPUT layer is GIVEN to second layer with adaptive feedforward weights.

Discussion

Explore topic-wise InterviewSolutions in .

In competitive learning, node with highest activation is the winner, is it true?(a) yes(b) noThis question was addressed to me by my college professor while I was bunking the class.Enquiry is from Feedback Layer in section Competitive Learning Neural Networks of Neural Networks

Generally how many kinds of pattern storage network exist?(a) 2(b) 3(c) 4(d) 5The question was posed to me in class test.I'd like to ask this question from Feedback Layer topic in chapter Competitive Learning Neural Networks of Neural Networks

What is ojas rule?(a) finds a unit weight vector(b) maximises the mean squared output(c) minimises the mean squared output(d) none of the mentionedI got this question during an interview for a job.The query is from Feedback Layer in chapter Competitive Learning Neural Networks of Neural Networks

By normalizing the weight at every stage can we prevent divergence?(a) yes(b) noThis question was addressed to me in unit test.I would like to ask this question from Feedback Layer topic in portion Competitive Learning Neural Networks of Neural Networks

How can divergence be prevented?(a) using hopfield criteria(b) sangers rule(c) ojas rule(d) sangers or ojas ruleThis question was posed to me in exam.The question is from Feedback Layer topic in section Competitive Learning Neural Networks of Neural Networks

The weight change inplain hebbian learning is?(a) 0(b) 1(c) 0 or 1(d) none of the mentionedThis question was posed to me in a job interview.I'm obligated to ask this question of Feedback Layer in division Competitive Learning Neural Networks of Neural Networks

An instar can respond to a set of input vectors even if its not trained to capture the behaviour of the set?(a) yes(b) noThe question was posed to me at a job interview.My doubt stems from Feedback Layer in section Competitive Learning Neural Networks of Neural Networks