100 + Interview Questions in Basics Of Artificial Neural Networks in Neural Networks Page 1 InterviewSolution

1.	In hebbian learning intial weights are set?(a) random(b) near to zero(c) near to target value(d) near to target valueThe question was posed to me at a job interview.The query is from Learning topic in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» The CORRECT option is (b) near to zero To explain I WOULD say: Hebb law LEAD to sum of correlations between input & output, inorder to achieve this, the starting initial WEIGHT values must be small.

Discussion

2.	Which of the following learning laws belongs to same category of learning?(a) hebbian, perceptron(b) perceptron, delta(c) hebbian, widrow-hoff(d) instar, outstarThe question was posed to me by my school teacher while I was bunking the class.The question is from Learning in division Basics of Artificial Neural Networks of Neural Networks
Answer» RIGHT option is (b) PERCEPTRON, delta Easy EXPLANATION: They both BELONGS to supervised type learning.

Discussion

3.	The instar learning law can be represented by equation?(a) ∆wjk= µ(bj – wjk), where the kth unit is the only active in the input layer(b) ∆wij= µ(bi – si) aj(c) ∆wij= µ(bi – si) aj Á(xi),wher Á(xi) is derivative of xi(d) ∆wij= µ(si) ajI had been asked this question during an online exam.My query is from Learning topic in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» Correct answer is (a) ∆wjk= µ(bj – wjk), where the KTH UNIT is the only active in the input layer Explanation: Follows from basic definition of OUTSTAR LEARNING LAW.

Discussion

4.	Is outstar a case of supervised learning?(a) yes(b) noI got this question in an online interview.The doubt is from Learning in section Basics of Artificial Neural Networks of Neural Networks
Answer» Right ANSWER is (a) yes For explanation I would SAY: SINCE weight ADJUSTMENT depend on target output, it is supervised learning.

Discussion

5.	Correlation learning law can be represented by equation?(a) ∆wij= µ(si) aj(b) ∆wij= µ(bi – si) aj(c) ∆wij= µ(bi – si) aj Á(xi),where Á(xi) is derivative of xi(d) ∆wij= µ bi ajI had been asked this question by my school principal while I was bunking the class.Asked question is from Learning topic in section Basics of Artificial Neural Networks of Neural Networks
Answer» RIGHT choice is (d) ∆wij= µ bi aj Easiest EXPLANATION: Correlation learning law depends on TARGET OUTPUT(bi).

Discussion

6.	The instar learning law can be represented by equation?(a) ∆wij= µ(si) aj(b) ∆wij= µ(bi – si) aj(c) ∆wij= µ(bi – si) aj Á(xi),where Á(xi) is derivative of xi(d) ∆wk= µ (a-wk), unit k with maximum output is identifiedI had been asked this question in examination.My query is from Learning in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» Correct answer is (d) ∆wk= µ (a-wk), UNIT k with MAXIMUM output is identified Easy explanation: Follows from BASIC definition of instar LEARNING law.

Discussion

7.	The other name for instar learning law?(a) looser take it all(b) winner take it all(c) winner give it all(d) looser give it allThe question was posed to me in a job interview.My enquiry is from Learning topic in portion Basics of Artificial Neural Networks of Neural Networks
Answer» Correct ANSWER is (B) winner take it all For explanation I WOULD say: The unit which GIVES maximum OUTPUT, weight is adjusted for that unit.

Discussion

8.	Is instar a case of supervised learning?(a) yes(b) noThis question was posed to me in class test.The question is from Learning in section Basics of Artificial Neural Networks of Neural Networks
Answer» RIGHT choice is (b) no The best EXPLANATION: Since WEIGHT adjustment don’t depend on TARGET output, it is UNSUPERVISED learning.

Discussion

9.	Correlation learning law is what type of learning?(a) supervised(b) unsupervised(c) either supervised or unsupervised(d) both supervised or unsupervisedI got this question in a job interview.I'm obligated to ask this question of Learning topic in portion Basics of Artificial Neural Networks of Neural Networks
Answer» CORRECT choice is (a) SUPERVISED For explanation: Supervised, SINCE depends on target output.

Discussion

10.	Correlation learning law is special case of?(a) Hebb learning law(b) Perceptron learning law(c) Delta learning law(d) LMS learning lawI got this question in homework.This interesting question is from Learning topic in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» The correct choice is (a) HEBB learning law The best EXPLANATION: Since in hebb is REPLACED by bi(target OUTPUT) in correlation.

Discussion

11.	Which of the following equation represent perceptron learning law?(a) ∆wij= µ(si) aj(b) ∆wij= µ(bi – si) aj(c) ∆wij= µ(bi – si) aj Á(xi),wher Á(xi) is derivative of xi(d) ∆wij= µ(bi – (wi a)) ajThe question was asked in an interview for job.I need to ask this question from Learning in section Basics of Artificial Neural Networks of Neural Networks
Answer» Right choice is (B) ∆wij= µ(bi – si) aj Best EXPLANATION: PERCEPTRON learning law is SUPERVISED, NONLINEAR type of learning.

Discussion

12.	What’s the other name of widrow & hoff learning law?(a) Hebb(b) LMS(c) MMS(d) None of the mentionedThe question was posed to me in an online quiz.My enquiry is from Learning in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» The CORRECT answer is (b) LMS The best explanation: LMS, LEAST mean square. Change in weight is made proportional to negative gradient of error & due to linearity of OUTPUT FUNCTION.

Discussion

13.	widrow & hoff learning law is special case of?(a) hebb learning law(b) perceptron learning law(c) delta learning law(d) none of the mentionedI got this question during an online exam.I would like to ask this question from Learning in portion Basics of Artificial Neural Networks of Neural Networks
Answer» Right choice is (c) DELTA LEARNING LAW Explanation: OUTPUT function in this law is assumed to be linear , all other THINGS same.

Discussion

14.	Delta learning is of unsupervised type?(a) yes(b) noThis question was addressed to me in quiz.The query is from Learning in section Basics of Artificial Neural Networks of Neural Networks
Answer» CORRECT CHOICE is (B) no To explain I would say: CHANGE in weight is based on the error between the desired & the actual OUTPUT values for a given input.

Discussion

15.	Hebb’s law can be represented by equation?(a) ∆wij= µf(wi a)aj(b) ∆wij= µ(si) aj, where (si) is output signal of ith input(c) both way(d) none of the mentionedThis question was posed to me in a national level competition.Question is from Learning in portion Basics of Artificial Neural Networks of Neural Networks
Answer» Correct option is (c) both way The EXPLANATION: (si)= f(wi a), in HEBB’s LAW.

Discussion

16.	If the change in weight vector is represented by ∆wij, what does it mean?(a) describes the change in weight vector for ith processing unit, taking input vector jth into account(b) describes the change in weight vector for jth processing unit, taking input vector ith into account(c) describes the change in weight vector for jth & ith processing unit.(d) none of the mentionedI have been asked this question in a job interview.My question comes from Learning topic in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» The correct answer is (a) describes the change in weight vector for ITH PROCESSING unit, TAKING INPUT vector jth into account The explanation is: ∆wij= µf(wi a)aj, where a is the input vector.

Discussion

17.	State which of the following statements hold foe perceptron learning law?(a) it is supervised type of learning law(b) it requires desired output for each input(c) ∆wij= µ(bi – si) aj(d) all of the mentionedThe question was asked in final exam.The query is from Learning in portion Basics of Artificial Neural Networks of Neural Networks
Answer» Correct option is (d) all of the mentioned The best explanation: all statements follow from ∆wij= µ(bi – si) AJ, where bi is the TARGET output & hence SUPERVISED learning.

Discussion

18.	State whether Hebb’s law is supervised learning or of unsupervised type?(a) supervised(b) unsupervised(c) either supervised or unsupervised(d) can be both supervised & unsupervisedI got this question at a job interview.Question is taken from Learning in division Basics of Artificial Neural Networks of Neural Networks
Answer» CORRECT choice is (B) unsupervised Explanation: No desired output is required for it’s IMPLEMENTATION.

Discussion

19.	What is learning signal in this equation ∆wij= µf(wi a)aj?(a) µ(b) wi a(c) aj(d) f(wi a)The question was posed to me in exam.The query is from Learning in portion Basics of Artificial Neural Networks of Neural Networks
Answer» Right OPTION is (d) f(wi a) Explanation: This the NON LINEAR representation of OUTPUT of the network.

Discussion

20.	On what parameters can change in weight vector depend?(a) learning parameters(b) input vector(c) learning signal(d) all of the mentionedThis question was addressed to me during an online interview.My question is based upon Learning in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» Right answer is (d) all of the mentioned The best explanation: Change in weight vector CORRESPONDING to jth input at time (t+1) depends on all of these PARAMETERS.

Discussion

21.	What LTM corresponds to?(a) activation state of network(b) encoded patterninformation pattern in synaptic weights(c) either way(d) both wayI have been asked this question during an interview.This intriguing question originated from Topology in division Basics of Artificial Neural Networks of Neural Networks
Answer» The correct choice is (b) encoded patterninformation pattern in synaptic weights Explanation: Long-term memory (LTM-the ENCODING and RETENTION of an effectively unlimited amount of INFORMATION for a much longer PERIOD of time) & hence the option.

Discussion

22.	What is STM in neural network?(a) short topology memory(b) stimulated topology memory(c) short term memory(d) none of the mentionedThe question was posed to me in exam.This interesting question is from Topology in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» The CORRECT option is (C) short TERM memory For EXPLANATION I would say: Full form of STM.

Discussion

23.	What does STM corresponds to?(a) activation state of network(b) encoded patterninformation pattern in synaptic weights(c) either way(d) both wayI had been asked this question during a job interview.The origin of the question is Topology in division Basics of Artificial Neural Networks of Neural Networks
Answer» The correct option is (a) activation state of network Easy explanation: Short-term memory (STM) refers to the capacity-limited retention of INFORMATION over a BRIEF period of time,HENCE the option.

Discussion

24.	Heteroassociative memory can be an example of which type of network?(a) group of instars(b) group of oustar(c) either group of instars or outstars(d) both group of instars or outstarsThe question was posed to me in an interview for internship.My doubt stems from Topology topic in division Basics of Artificial Neural Networks of Neural Networks
Answer» Correct answer is (C) either GROUP of instars or outstars Best explanation: Depending UPON the flow, the memory can be of either of the type.

Discussion

25.	If two layers coincide & weights are symmetric(wij=wji), then what is that structure called?(a) instar(b) outstar(c) autoassociative memory(d) heteroassociative memoryThe question was asked at a job interview.My question is from Topology in division Basics of Artificial Neural Networks of Neural Networks
Answer» Right ANSWER is (c) autoassociative memory The BEST I can explain: In autoassociative memory each UNIT is connected to EVERY other unit & to itself.

Discussion

26.	The operation of outstar can be viewed as?(a) content addressing the memory(b) memory addressing the content(c) either content addressing or memory addressing(d) both content & memory addressingThis question was posed to me in class test.This key question is from Topology in division Basics of Artificial Neural Networks of Neural Networks
Answer» CORRECT answer is (b) memory ADDRESSING the content The explanation: Because in outstar, when weight vector for connections from jth unit (say) in F2 approaches the activity PATTERN inF1(comprises of input vector).

Discussion

27.	The operation of instar can be viewed as?(a) content addressing the memory(b) memory addressing the content(c) either content addressing or memory addressing(d) both content & memory addressingI got this question in quiz.My question comes from Topology in portion Basics of Artificial Neural Networks of Neural Networks
Answer» RIGHT choice is (a) content addressing the memory The explanation is: Because in instar, when input is given to layer F1, the the JTH(SAY) unit of other layer F2 will be activated to maximum extent.

Discussion

28.	What is an outstar topology?(a) when input is given to layer F1, the the jth(say) unit of other layer F2 will be activated to maximum extent(b) when weight vector for connections from jth unit (say) in F2 approaches the activity pattern inF1(comprises of input vector)(c) can be either way(d) none of the mentionedThis question was addressed to me in an internship interview.I'd like to ask this question from Topology topic in division Basics of Artificial Neural Networks of Neural Networks
Answer» CORRECT OPTION is (b) when weight vector for connections from jth unit (say) in F2 APPROACHES the activity pattern inF1(comprises of input vector) The EXPLANATION: Restatement of basic definitionof outstar.

Discussion

29.	What is an instar topology?(a) when input is given to layer F1, the the jth(say) unit of other layer F2 will be activated to maximum extent(b) when weight vector for connections from jth unit (say) in F2 approaches the activity pattern inF1(comprises of input vector)(c) can be either way(d) none of the mentionedThis question was addressed to me during an interview.My question comes from Topology topic in section Basics of Artificial Neural Networks of Neural Networks
Answer» Correct option is (a) when INPUT is GIVEN to LAYER F1, the the jth(say) unit of other layer F2 will be activated to maximum extent Explanation: RESTATEMENT of basic definitionof instar.

Discussion

30.	Connections across the layers in standard topologies & among the units within a layer can be organised?(a) in feedforward manner(b) in feedback manner(c) both feedforward & feedback(d) either feedforward & feedbackI have been asked this question by my college professor while I was bunking the class.Question is taken from Topology in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» The correct option is (d) either FEEDFORWARD & feedback The explanation: Connections ACROSS the layers in standard topologies can be in feedforward manner or in feedback manner but not both.

Discussion

31.	In neural how can connectons between different layers be achieved?(a) interlayer(b) intralayer(c) both interlayer and intralayer(d) either interlayer or intralayerThe question was posed to me in final exam.I'd like to ask this question from Topology topic in section Basics of Artificial Neural Networks of Neural Networks
Answer» The correct answer is (c) both interlayer and intralayer Easiest explanation: Connections between layers can be MADE to ONE UNIT to another and within the UNITS of a layer.

Discussion

32.	what is the another name of weight update rule in adalinemodel based on its functionality?(a) LMS error learning law(b) gradient descent algorithm(c) both LMS error & gradient descent learning law(d) none of the mentionedThis question was addressed to me in an online quiz.Asked question is from Models in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» The correct answer is (C) both LMS error & gradient descent LEARNING law To EXPLAIN: weight UPDATE rule minimizesthe mean squared error(delta square), averaged over all inputs & this laws is derived using negative gradient of error surface weight space, hence option a & b.

Discussion

33.	In adaline model what is the relation between output & activation value(x)?(a) linear(b) nonlinear(c) can be either linear or non-linear(d) none of the mentionedThis question was posed to me during an online exam.The origin of the question is Models topic in division Basics of Artificial Neural Networks of Neural Networks
Answer» RIGHT OPTION is (a) LINEAR The EXPLANATION: s,output=f(x)=x. Hence its a linear model.

Discussion

34.	What was the main point of difference between the adaline & perceptron model?(a) weights are compared with output(b) sensory units result is compared with output(c) analog activation value is compared with output(d) all of the mentionedThis question was posed to me at a job interview.This interesting question is from Models in portion Basics of Artificial Neural Networks of Neural Networks
Answer» CORRECT OPTION is (c) analog activation value is compared with output The best explanation: Analog activation value comparison with output,instead of desired output as in perceptron model was the main POINT of DIFFERENCE between the adaline & perceptron model.

Discussion

35.	who invented the adaline neural model?(a) Rosenblatt(b) Hopfield(c) Werbos(d) WidrowThe question was posed to me during a job interview.The doubt is from Models in section Basics of Artificial Neural Networks of Neural Networks
Answer» Right choice is (d) Widrow Easiest EXPLANATION: Widrow INVENTED the ADALINE NEURAL MODEL.

Discussion

36.	If a(i) is the input, ^ is the error, n is the learning parameter, then how can weight change in a perceptron model be represented?(a) na(i)(b) n^(c) ^a(i)(d) none of the mentionedI have been asked this question in class test.This interesting question is from Models in division Basics of Artificial Neural Networks of Neural Networks
Answer» The CORRECT choice is (d) NONE of the mentioned For EXPLANATION I would say: The correct answer is n^a(i).

Discussion

37.	What is adaline in neural networks?(a) adaptive linear element(b) automatic linear element(c) adaptive line element(d) none of the mentionedI had been asked this question in an international level competition.My question comes from Models in section Basics of Artificial Neural Networks of Neural Networks
Answer» Correct option is (a) ADAPTIVE LINEAR element Easy EXPLANATION: adaptive linear element is the FULL form of adaline neural model.

Discussion

38.	What is delta (error) in perceptron model of neuron?(a) error due to environmental condition(b) difference between desired & target output(c) can be both due to difference in target output or environmental condition(d) none of the mentionedThe question was posed to me during an online exam.The query is from Models topic in portion Basics of Artificial Neural Networks of Neural Networks
Answer» Correct answer is (a) error due to environmental condition To explain: All other PARAMETERS are ASSUMED to be null while calculatin the error in perceptron MODEL & only difference between DESIRED & target output is TAKEN into account.

Discussion

39.	What was the main deviation in perceptron model from that of MP model?(a) more inputs can be incorporated(b) learning enabled(c) all of the mentioned(d) none of the mentionedI have been asked this question in class test.This key question is from Models topic in division Basics of Artificial Neural Networks of Neural Networks
Answer» Right answer is (b) LEARNING enabled The EXPLANATION is: The weights in perceprton MODEL are ADJUSTABLE.

Discussion

40.	What was the 2nd stage in perceptron model called?(a) sensory units(b) summing unit(c) association unit(d) output unitI had been asked this question during an interview.The query is from Models in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» The correct choice is (C) association unit For explanation I WOULD say: This was the very speciality of the perceptron model, that is PERFORMS association mapping on OUTPUTS of he SENSORY units.

Discussion

41.	Does McCulloch-pitts model have ability of learning?(a) yes(b) noThe question was asked by my college director while I was bunking the class.My question is based upon Models topic in section Basics of Artificial Neural Networks of Neural Networks
Answer» The CORRECT answer is (B) no For explanation I WOULD say: Weights are FIXED.

Discussion

42.	Who invented perceptron neural networks?(a) McCullocch-pitts(b) Widrow(c) Minsky & papert(d) RosenblattI got this question by my college professor while I was bunking the class.This is a very interesting question from Models topic in division Basics of Artificial Neural Networks of Neural Networks
Answer» Correct choice is (d) Rosenblatt The explanation is: The perceptron is one of the earliest neural networks. INVENTED at the Cornell Aeronautical Laboratory in 1957 by Frank Rosenblatt, the Perceptron was an ATTEMPT to UNDERSTAND human MEMORY, learning, and cognitive processes.

Discussion

43.	When both inputs are different, what will be the logical output of the figure of question 4?(a) 0(b) 1(c) either 0 or 1(d) zI have been asked this question in a national level competition.My question is taken from Models in section Basics of Artificial Neural Networks of Neural Networks
Answer» RIGHT OPTION is (a) 0 Easy EXPLANATION: Check the TRUTH table of nor gate.

Discussion

44.	When both inputs are 1, what will be the output of the pitts model nand gate ?(a) 0(b) 1(c) either 0 or 1(d) zThis question was addressed to me in class test.My question comes from Models in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» RIGHT option is (a) 0 The explanation: Check the TRUTH table of SIMPLY a nand GATE.

Discussion

45.	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 pittsThe question was posed to me during an online interview.I'm obligated to ask this question of Models in portion Basics of Artificial Neural Networks of Neural Networks
Answer» RIGHT CHOICE is (b) rosenblatt PERCEPTRON model Explanation: Weights are fixed in pitts model but adjustable in rosenblatt.

Discussion

46.	When both inputs are different, what will be the output of the above figure?(a) 0(b) 1(c) either 0 or 1(d) zThis question was posed to me in semester exam.Enquiry is from Models in division Basics of Artificial Neural Networks of Neural Networks
Answer» Correct answer is (a) 0 To EXPLAIN I would say: Check the TRUTH table of nor GATE.

Discussion

47.	When both inputs are 1, what will be the output of the above figure?(a) 0(b) 1(c) either 0 or 1(d) zI had been asked this question by my college professor while I was bunking the class.My question is from Models topic in division Basics of Artificial Neural Networks of Neural Networks
Answer» RIGHT CHOICE is (a) 0 To ELABORATE: CHECK the truth table of nor gate.

Discussion

48.	If ‘b’ in the figure below is the bias, then what logic circuit does it represents?(a) or gate(b) and gate(c) nor gate(d) nand gateI have been asked this question by my school teacher while I was bunking the class.This intriguing question comes from Models topic in chapter Basics of Artificial Neural Networks of Neural Networks
Answer» The CORRECT option is (c) nor gate To elaborate: FORM the truth table of above FIGURE by TAKING inputs as 0 or 1.

Discussion

49.	What does the character ‘b’ represents in the above diagram?(a) bias(b) any constant value(c) a variable value(d) none of the mentionedI have been asked this question in an interview.Question is from Models in section Basics of Artificial Neural Networks of Neural Networks
Answer» CORRECT option is (a) BIAS Explanation: More APPROPRIATE choice since bias is a constant FIXED value for any circuit model.

Discussion

50.	What is nature of function F(x) in the figure?(a) linear(b) non-linear(c) can be either linear or non-linear(d) none of the mentionedI have been asked this question in quiz.I would like to ask this question from Models in division Basics of Artificial Neural Networks of Neural Networks
Answer» RIGHT ANSWER is (b) non-linear Best EXPLANATION: In this FUNCTION, the independent variable is an exponent in the equation hence non-linear.

Discussion

Explore topic-wise InterviewSolutions in .

In hebbian learning intial weights are set?(a) random(b) near to zero(c) near to target value(d) near to target valueThe question was posed to me at a job interview.The query is from Learning topic in chapter Basics of Artificial Neural Networks of Neural Networks

Is outstar a case of supervised learning?(a) yes(b) noI got this question in an online interview.The doubt is from Learning in section Basics of Artificial Neural Networks of Neural Networks

The other name for instar learning law?(a) looser take it all(b) winner take it all(c) winner give it all(d) looser give it allThe question was posed to me in a job interview.My enquiry is from Learning topic in portion Basics of Artificial Neural Networks of Neural Networks

Is instar a case of supervised learning?(a) yes(b) noThis question was posed to me in class test.The question is from Learning in section Basics of Artificial Neural Networks of Neural Networks

Correlation learning law is special case of?(a) Hebb learning law(b) Perceptron learning law(c) Delta learning law(d) LMS learning lawI got this question in homework.This interesting question is from Learning topic in chapter Basics of Artificial Neural Networks of Neural Networks

What’s the other name of widrow & hoff learning law?(a) Hebb(b) LMS(c) MMS(d) None of the mentionedThe question was posed to me in an online quiz.My enquiry is from Learning in chapter Basics of Artificial Neural Networks of Neural Networks

widrow & hoff learning law is special case of?(a) hebb learning law(b) perceptron learning law(c) delta learning law(d) none of the mentionedI got this question during an online exam.I would like to ask this question from Learning in portion Basics of Artificial Neural Networks of Neural Networks

Delta learning is of unsupervised type?(a) yes(b) noThis question was addressed to me in quiz.The query is from Learning in section Basics of Artificial Neural Networks of Neural Networks

What is learning signal in this equation ∆wij= µf(wi a)aj?(a) µ(b) wi a(c) aj(d) f(wi a)The question was posed to me in exam.The query is from Learning in portion Basics of Artificial Neural Networks of Neural Networks

On what parameters can change in weight vector depend?(a) learning parameters(b) input vector(c) learning signal(d) all of the mentionedThis question was addressed to me during an online interview.My question is based upon Learning in chapter Basics of Artificial Neural Networks of Neural Networks

What is STM in neural network?(a) short topology memory(b) stimulated topology memory(c) short term memory(d) none of the mentionedThe question was posed to me in exam.This interesting question is from Topology in chapter Basics of Artificial Neural Networks of Neural Networks

who invented the adaline neural model?(a) Rosenblatt(b) Hopfield(c) Werbos(d) WidrowThe question was posed to me during a job interview.The doubt is from Models in section Basics of Artificial Neural Networks of Neural Networks

What was the 2nd stage in perceptron model called?(a) sensory units(b) summing unit(c) association unit(d) output unitI had been asked this question during an interview.The query is from Models in chapter Basics of Artificial Neural Networks of Neural Networks

Does McCulloch-pitts model have ability of learning?(a) yes(b) noThe question was asked by my college director while I was bunking the class.My question is based upon Models topic in section Basics of Artificial Neural Networks of Neural Networks

Who invented perceptron neural networks?(a) McCullocch-pitts(b) Widrow(c) Minsky & papert(d) RosenblattI got this question by my college professor while I was bunking the class.This is a very interesting question from Models topic in division Basics of Artificial Neural Networks of Neural Networks

When both inputs are different, what will be the logical output of the figure of question 4?(a) 0(b) 1(c) either 0 or 1(d) zI have been asked this question in a national level competition.My question is taken from Models in section Basics of Artificial Neural Networks of Neural Networks

When both inputs are 1, what will be the output of the pitts model nand gate ?(a) 0(b) 1(c) either 0 or 1(d) zThis question was addressed to me in class test.My question comes from Models in chapter Basics of Artificial Neural Networks of Neural Networks

When both inputs are different, what will be the output of the above figure?(a) 0(b) 1(c) either 0 or 1(d) zThis question was posed to me in semester exam.Enquiry is from Models in division Basics of Artificial Neural Networks of Neural Networks

When both inputs are 1, what will be the output of the above figure?(a) 0(b) 1(c) either 0 or 1(d) zI had been asked this question by my college professor while I was bunking the class.My question is from Models topic in division Basics of Artificial Neural Networks of Neural Networks

What does the character ‘b’ represents in the above diagram?(a) bias(b) any constant value(c) a variable value(d) none of the mentionedI have been asked this question in an interview.Question is from Models in section Basics of Artificial Neural Networks of Neural Networks

What is nature of function F(x) in the figure?(a) linear(b) non-linear(c) can be either linear or non-linear(d) none of the mentionedI have been asked this question in quiz.I would like to ask this question from Models in division Basics of Artificial Neural Networks of Neural Networks