90 + Interview Questions in Feedback Neural Networks in Neural Networks Page 2 InterviewSolution

51.	When are false wells created?(a) when number of patterns is more than number of basins of attraction(b) when number of patterns is less than number of basins of attraction(c) when number of patterns is same as number of basins of attraction(d) none of the mentionedI had been asked this question in an interview for internship.My enquiry is from Analysis of Pattern Storage Networks in chapter Feedback Neural Networks of Neural Networks
Answer» The correct choice is (b) when number of patterns is LESS than number of BASINS of attraction For explanation I WOULD SAY: Explanation: False WELLS are created when number of patterns is less than number of basins of attraction.

Discussion

52.	When does storage problem becomes hard problem?(a) when number of patterns is more than number of basins of attraction(b) when number of patterns is less than number of basins of attraction(c) when number of patterns is same as number of basins of attraction(d) none of the mentionedI have been asked this question during a job interview.My query is from Analysis of Pattern Storage Networks in division Feedback Neural Networks of Neural Networks
Answer» Correct answer is (a) when NUMBER of patterns is more than number of basins of attraction The BEST explanation: Explanation: When number of patterns is more than number of basins of attraction then STORAGE problem becomes HARD problem.

Discussion

53.	What is hopfield model?(a) fully connected feedback network(b) fully connected feedback networkwith symmetric weights(c) fully connected feedforward network(d) fully connected feedback network with symmetric weightsThis question was addressed to me in a job interview.My enquiry is from Analysis of Pattern Storage Networks topic in chapter Feedback Neural Networks of Neural Networks
Answer» RIGHT option is (b) fully connected FEEDBACK networkwith symmetric weights To ELABORATE: EXPLANATION: Hopfield model is fully connected feedback networkwith symmetric weights.

Discussion

54.	What happens when number of patterns is more than number of basins of attraction?(a) false wells(b) storage problem becomes hard problem(c) no storage and recall can take place(d) none of the mentionedI got this question in an online quiz.Asked question is from Analysis of Pattern Storage Networks in portion Feedback Neural Networks of Neural Networks
Answer» CORRECT answer is (b) STORAGE problem becomes HARD problem Easiest explanation: Explanation: When NUMBER of patterns is more than number of basins of attraction then storage problem becomes hard problem.

Discussion

55.	What happens when number of patterns is less than number of basins of attraction?(a) false wells(b) storage problem becomes hard problem(c) no storage and recall can take place(d) none of the mentionedI have been asked this question in an online interview.Query is from Analysis of Pattern Storage Networks topic in section Feedback Neural Networks of Neural Networks
Answer» Right choice is (a) FALSE WELLS To elaborate: EXPLANATION: False wells are CREATED when number of PATTERNS is less than number of basins of attraction.

Discussion

56.	Number of desired patterns is what of basins of attraction?(a) dependent(b) independent(c) dependent or independent(d) none of the mentionedI got this question in a national level competition.The query is from Analysis of Pattern Storage Networks topic in chapter Feedback Neural Networks of Neural Networks
Answer» Correct CHOICE is (b) independent The best EXPLANATION: Explanation: Number of desired PATTERNS is independent of BASINS of attraction.

Discussion

57.	Can probability of error in recall be reduced?(a) yes(b) noThis question was addressed to me during an online exam.Origin of the question is Analysis of Pattern Storage Networks topic in section Feedback Neural Networks of Neural Networks
Answer» The correct OPTION is (a) yes Easiest EXPLANATION: Explanation: Probability of error in recall be reduced by adjusting weights in such a WAY that it is matched to probability distribution of desired PATTERNS.

Discussion

58.	Is it possible to determine exact number of basins of attraction in energy landscape?(a) yes(b) noThe question was asked during an online interview.Question is taken from Analysis of Pattern Storage Networks in section Feedback Neural Networks of Neural Networks
Answer» Right answer is (b) no To elaborate: Explanation: It is not possible to determine EXACT NUMBER of basins of attraction in energy LANDSCAPE.

Discussion

59.	For what purpose energyminima are used?(a) pattern classification(b) patten mapping(c) pattern storage(d) none of the mentionedI have been asked this question in an international level competition.This intriguing question originated from Analysis of Pattern Storage Networks in portion Feedback Neural Networks of Neural Networks
Answer» The correct CHOICE is (c) PATTERN storage Explanation: Explanation: Energyminima are USED for pattern storage.

Discussion

60.	What is capacity of a network?(a) number of inputs it can take(b) number of output it can deliver(c) number of patterns that can be stored(d) none of the mentionedThis question was posed to me in an interview for job.My doubt stems from Analysis of Pattern Storage Networks topic in division Feedback Neural Networks of Neural Networks
Answer» Correct OPTION is (c) number of patterns that can be stored EXPLANATION: Explanation: The CAPACITY of a network is the number of patterns that can be stored.

Discussion

61.	When does storage problem becomes hard problem?(a) when number of patterns is more than number of basins of attraction(b) when number of patterns is less than number of basins of attraction(c) when number of patterns is same as number of basins of attraction(d) none of the mentionedI had been asked this question by my college professor while I was bunking the class.This is a very interesting question from Analysis of Pattern Storage Networks topic in portion Feedback Neural Networks of Neural Networks
Answer» The CORRECT answer is (a) when number of PATTERNS is more than number of basins of attraction The explanation: Explanation: When number of patterns is more than number of basins of attraction then STORAGE problem becomes hard problem.

Discussion

62.	What happens when number of patterns is less than number of basins of attraction?(a) false wells(b) storage problem becomes hard problem(c) no storage and recall can take place(d) none of the mentionedThis question was posed to me in an interview for job.The query is from Analysis of Pattern Storage Networks topic in section Feedback Neural Networks of Neural Networks
Answer» Right option is (a) FALSE wells To EXPLAIN: EXPLANATION: False wells are created when NUMBER of patterns is less than number of basins of attraction.

Discussion

63.	When are false wells created?(a) when number of patterns is more than number of basins of attraction(b) when number of patterns is less than number of basins of attraction(c) when number of patterns is same as number of basins of attraction(d) none of the mentionedThis question was addressed to me during a job interview.My question is from Analysis of Pattern Storage Networks topic in division Feedback Neural Networks of Neural Networks
Answer» CORRECT choice is (B) when NUMBER of patterns is LESS than number of basins of ATTRACTION For explanation I would say: Explanation: False wells are created when number of patterns is less than number of basins of attraction.

Discussion

64.	What is hopfield model?(a) fully connected feedback network(b) fully connected feedback networkwith symmetric weights(c) fully connected feedforward network(d) fully connected feedback network with symmetric weightsThis question was posed to me in a job interview.Enquiry is from Analysis of Pattern Storage Networks in chapter Feedback Neural Networks of Neural Networks
Answer» The CORRECT CHOICE is (b) fully connected feedback networkwith symmetric WEIGHTS The explanation: Explanation: Hopfield MODEL is fully connected feedback networkwith symmetric weights.

Discussion

65.	What happens when number of patterns is more than number of basins of attraction?(a) false wells(b) storage problem becomes hard problem(c) no storage and recall can take place(d) none of the mentionedThe question was posed to me in examination.This is a very interesting question from Analysis of Pattern Storage Networks topic in section Feedback Neural Networks of Neural Networks
Answer» The correct option is (B) STORAGE problem BECOMES HARD problem The best I can EXPLAIN: Explanation: When number of patterns is more than number of basins of attraction then storage problem becomes hard problem.

Discussion

66.	What is capacity of a network?(a) number of inputs it can take(b) number of output it can deliver(c) number of patterns that can be stored(d) none of the mentionedI had been asked this question during an interview.Enquiry is from Analysis of Pattern Storage Networks in chapter Feedback Neural Networks of Neural Networks
Answer» CORRECT OPTION is (C) NUMBER of patterns that can be STORED Easiest explanation: Explanation: The capacity of a network is the number of patterns that can be stored.

Discussion

67.	Can probability of error in recall be reduced?(a) yes(b) noThis question was addressed to me during an online exam.I need to ask this question from Analysis of Pattern Storage Networks in chapter Feedback Neural Networks of Neural Networks
Answer» Right option is (a) yes Best EXPLANATION: Explanation: Probability of error in recall be reduced by adjusting weights in such a WAY that it is matched to probability DISTRIBUTION of DESIRED PATTERNS.

Discussion

68.	Number of desired patterns is what of basins of attraction?(a) dependent(b) independent(c) dependent or independent(d) none of the mentionedThe question was posed to me during an interview for a job.My question is based upon Analysis of Pattern Storage Networks in division Feedback Neural Networks of Neural Networks
Answer» The correct CHOICE is (b) independent Explanation: Explanation: Number of DESIRED patterns is independent of BASINS of attraction.

Discussion

69.	Is it possible to determine exact number of basins of attraction in energy landscape?(a) yes(b) noThis question was addressed to me during an internship interview.Question is taken from Analysis of Pattern Storage Networks in division Feedback Neural Networks of Neural Networks
Answer» Right OPTION is (b) no To elaborate: EXPLANATION: It is not POSSIBLE to determine exact number of BASINS of attraction in energy landscape.

Discussion

70.	For what purpose energyminima are used?(a) pattern classification(b) patten mapping(c) pattern storage(d) none of the mentionedI got this question in semester exam.Asked question is from Analysis of Pattern Storage Networks in division Feedback Neural Networks of Neural Networks
Answer» Correct OPTION is (c) PATTERN storage Easy EXPLANATION: Explanation: Energyminima are used for pattern storage.

Discussion

71.	What does basins of attraction corresponds to?(a) stable states(b) unstable states(c) neutral states(d) none of the mentionedThis question was addressed to me during an online interview.Asked question is from Analysis of Linear Autoassociative FF Network topic in section Feedback Neural Networks of Neural Networks
Answer» RIGHT CHOICE is (a) stable STATES Explanation: BASINS of attraction CORRESPONDS to the regions of stable equilibrium states.

Discussion

72.	What is the effect of basins of attraction on energy landscape?(a) leads to small deviations(b) leads to fluctuation around(c) may lead to deviation or fluctuation depends on external noise(d) none of the mentionedThe question was asked in class test.This interesting question is from Analysis of Linear Autoassociative FF Network topic in division Feedback Neural Networks of Neural Networks
Answer» The correct ANSWER is (a) leads to small DEVIATIONS For explanation: BASINS of attraction in energy LANDSCAPE leads to small deviations.

Discussion

73.	Basins of attraction in energy landscape leads to fluctuations, is that true?(a) yes(b) noThe question was asked in a national level competition.Enquiry is from Analysis of Linear Autoassociative FF Network in chapter Feedback Neural Networks of Neural Networks
Answer» RIGHT answer is (B) no The explanation: Basins of attraction in ENERGY LANDSCAPE leads to only small deviations.

Discussion

74.	What may create basins of attraction in energy landscape?(a) feedback among units(b) nonlinear processing in units(c) both feedback and nonlinear processing in units(d) none of the mentionedI had been asked this question during an interview.This key question is from Analysis of Linear Autoassociative FF Network in division Feedback Neural Networks of Neural Networks
Answer» The correct choice is (c) both feedback and nonlinear processing in UNITS The explanation: Feedback and nonlinear processing in units MAY CREATE basins of ATTRACTION in energy landscape.

Discussion

75.	whatdo you mean by the term trajectory of states?(a) just a state of the network(b) sates at energy minima(c) states at energy maxima(d) none of the mentionedThe question was asked by my school principal while I was bunking the class.Origin of the question is Analysis of Linear Autoassociative FF Network topic in section Feedback Neural Networks of Neural Networks
Answer» Right answer is (d) none of the mentioned To EXPLAIN: The term TRAJECTORY of states means state of the NETWORK at successive instants of TIME.

Discussion

76.	What determines shape of energy landscape?(a) network parameters(b) network states(c) both network parameter and states(d) none of the mentionedThis question was addressed to me in homework.My question comes from Analysis of Linear Autoassociative FF Network in portion Feedback Neural Networks of Neural Networks
Answer» RIGHT OPTION is (c) both network parameter and STATES To ELABORATE: The shape of energy landscape is DETERMINED by network parameter and states.

Discussion

77.	The trajectory of the state is determined by?(a) activation dynamics(b) synaptic dynamics(c) both activation and synaptic dynamics(d) none of the mentionedI had been asked this question in an interview for job.I would like to ask this question from Analysis of Linear Autoassociative FF Network in section Feedback Neural Networks of Neural Networks
Answer» Right answer is (a) ACTIVATION DYNAMICS Easy EXPLANATION: The TRAJECTORY of the STATEIS determined by activation dynamics.

Discussion

78.	Can data be stored through weights?(a) yes(b) noThis question was posed to me by my school teacher while I was bunking the class.Origin of the question is Analysis of Linear Autoassociative FF Network in section Feedback Neural Networks of Neural Networks
Answer» Right OPTION is (a) yes The EXPLANATION is: Data can be STORED through weights as in case of binary PATTERNS.

Discussion

79.	How is pattern storage task generally accomplished?(a) by a feedback network consisting of processing units with non linear output functions(b) by a feedback network consisting of processing units with linear output functions(c) by a feedforward network consisting of processing units with non linear output functions(d) by a feedforward network consisting of processing units with linear output functionsI have been asked this question during a job interview.My question is taken from Analysis of Linear Autoassociative FF Network topic in portion Feedback Neural Networks of Neural Networks
Answer» Correct option is (b) by a feedback NETWORK consisting of PROCESSING UNITS with LINEAR output FUNCTIONS Explanation: Pattern storage task generally accomplished by a feedback network consisting of processing units with non linear output functions.

Discussion

80.	What is the objective of pattern recall?(a) it should not take place when relations are disturbed(b) it should take place when relations are slightly disturbed(c) there is no such objective of recall, it depends on the system(d) none of the mentionedThe question was asked in my homework.My question is taken from Analysis of Linear Autoassociative FF Network topic in section Feedback Neural Networks of Neural Networks
Answer» RIGHT option is (B) it should take place when RELATIONS are slightly disturbed For explanation: The pattern recall should take place even THOUGH features and their SPATIAL relations are slightly disturbed due to noise.

Discussion

81.	Linear neurons can be useful for application such as interpolation, is it true?(a) yes(b) noThis question was addressed to me in semester exam.Asked question is from Introduction of Feedback Neural Network in chapter Feedback Neural Networks of Neural Networks
Answer» The correct CHOICE is (a) yes For explanation I would SAY: This means for INPUT vector x, output vector y is PRODUCED and for input a.x, output will be a.y.

Discussion

82.	What is the objective of a pattern storage task in a network?(a) to store a given set of patterns(b) to recall a give set of patterns(c) both to store and recall(d) none of the mentionedI have been asked this question by my college director while I was bunking the class.My question is from Introduction of Feedback Neural Network in portion Feedback Neural Networks of Neural Networks
Answer» CORRECT choice is (c) both to STORE and recall To explain: The objective of a pattern storage task in a network is to store and recall a GIVEN set of PATTERNS.

Discussion

83.	What property should a feedback network have, to make it useful for storing information?(a) accretive behaviour(b) interpolative behaviour(c) both accretive and interpolative behaviour(d) none of the mentionedI had been asked this question in a national level competition.I want to ask this question from Introduction of Feedback Neural Network topic in chapter Feedback Neural Networks of Neural Networks
Answer» CORRECT choice is (a) accretive behaviour For explanation I would say: During recall accretive behaviour make it POSSIBLE for system to STORE INFORMATION.

Discussion

84.	If input is ‘ a(l) + e ‘ where ‘e’is the noise introduced, then what is the output if system is interpolative in nature?(a) a(l)(b) a(l) + e(c) could be either a(l) or a(l) + e(d) eI got this question in unit test.The above asked question is from Introduction of Feedback Neural Network in section Feedback Neural Networks of Neural Networks
Answer» CORRECT ANSWER is (b) a(L) + e Best EXPLANATION: This is the property of interpolative SYSTEM.

Discussion

85.	If input is ‘ a(l) + e ‘ where ‘e’is the noise introduced, then what is the output if system is accretive in nature?(a) a(l)(b) a(l) + e(c) could be either a(l) or a(l) + e(d) eI got this question in quiz.Query is from Introduction of Feedback Neural Network topic in section Feedback Neural Networks of Neural Networks
Answer» The CORRECT answer is (a) a(L) The EXPLANATION: This is the PROPERTY of ACCRETIVE system.

Discussion

86.	If input is ‘ a(l) + e ‘ where ‘e’is the noise introduced, then what is the output in case of autoassociative feedback network?(a) a(l)(b) a(l) + e(c) could be either a(l) or a(l) + e(d) eThis question was addressed to me in quiz.This key question is from Introduction of Feedback Neural Network in division Feedback Neural Networks of Neural Networks
Answer» Right CHOICE is (b) a(L) + e Explanation: This is DUE to the ABSENCE of accretive BEHAVIOUR.

Discussion

87.	Is there any error in linear autoassociative networks?(a) yes(b) noThis question was addressed to me in examination.I would like to ask this question from Introduction of Feedback Neural Network in division Feedback Neural Networks of Neural Networks
Answer» The correct CHOICE is (B) no Easiest EXPLANATION: Because input comes out as OUTPUT.

Discussion

88.	What is objective of linear autoassociative feedforward networks?(a) to associate a given pattern with itself(b) to associate a given pattern with others(c) to associate output with input(d) none of the mentionedThis question was posed to me by my college professor while I was bunking the class.My enquiry is from Introduction of Feedback Neural Network topic in section Feedback Neural Networks of Neural Networks
Answer» RIGHT answer is (a) to associate a GIVEN pattern with itself The EXPLANATION: The OBJECTIVE of linear autoassociative feedforward networks is to associate a given pattern with itself.

Discussion

89.	What is a Boltzman machine?(a) A feedback network with hidden units(b) A feedback network with hidden units and probabilistic update(c) A feed forward network with hidden units(d) A feed forward network with hidden units and probabilistic updateThe question was posed to me in an online quiz.My question is taken from Introduction of Feedback Neural Network in chapter Feedback Neural Networks of Neural Networks
Answer» Correct OPTION is (b) A FEEDBACK network with hidden units and probabilistic update Explanation: BOLTZMAN MACHINE is a feedback network with hidden units and probabilistic update.

Discussion

90.	How can false minima be reduced in case of error in recall in feedback neural networks?(a) by providing additional units(b) by using probabilistic update(c) can be either probabilistic update or using additional units(d) none of the mentionedThis question was posed to me in my homework.This intriguing question originated from Introduction of Feedback Neural Network topic in division Feedback Neural Networks of Neural Networks
Answer» CORRECT answer is (b) by USING probabilistic update The best EXPLANATION: HARD problem can be solved by ADDITIONAL units not the false minima.

Discussion

Explore topic-wise InterviewSolutions in .

Can probability of error in recall be reduced?(a) yes(b) noThis question was addressed to me during an online exam.Origin of the question is Analysis of Pattern Storage Networks topic in section Feedback Neural Networks of Neural Networks

Is it possible to determine exact number of basins of attraction in energy landscape?(a) yes(b) noThe question was asked during an online interview.Question is taken from Analysis of Pattern Storage Networks in section Feedback Neural Networks of Neural Networks

Can probability of error in recall be reduced?(a) yes(b) noThis question was addressed to me during an online exam.I need to ask this question from Analysis of Pattern Storage Networks in chapter Feedback Neural Networks of Neural Networks

Is it possible to determine exact number of basins of attraction in energy landscape?(a) yes(b) noThis question was addressed to me during an internship interview.Question is taken from Analysis of Pattern Storage Networks in division Feedback Neural Networks of Neural Networks

For what purpose energyminima are used?(a) pattern classification(b) patten mapping(c) pattern storage(d) none of the mentionedI got this question in semester exam.Asked question is from Analysis of Pattern Storage Networks in division Feedback Neural Networks of Neural Networks

Basins of attraction in energy landscape leads to fluctuations, is that true?(a) yes(b) noThe question was asked in a national level competition.Enquiry is from Analysis of Linear Autoassociative FF Network in chapter Feedback Neural Networks of Neural Networks

Can data be stored through weights?(a) yes(b) noThis question was posed to me by my school teacher while I was bunking the class.Origin of the question is Analysis of Linear Autoassociative FF Network in section Feedback Neural Networks of Neural Networks

Linear neurons can be useful for application such as interpolation, is it true?(a) yes(b) noThis question was addressed to me in semester exam.Asked question is from Introduction of Feedback Neural Network in chapter Feedback Neural Networks of Neural Networks

Is there any error in linear autoassociative networks?(a) yes(b) noThis question was addressed to me in examination.I would like to ask this question from Introduction of Feedback Neural Network in division Feedback Neural Networks of Neural Networks