Q. Intersection of convex regions in three layer network can only produce convex surfaces, is the statement true?

View solution

Q. If the output produces nonconvex regions, then how many layered neural is required at minimum?

View solution

Q. Can all hard problems be handled by a multilayer feedforward neural network, with nonlinear units?

View solution

Q. What is a mapping problem?

View solution

Q. Can mapping problem be a more general case of pattern classification problem?

View solution

Q. What is the objective of pattern mapping problem?

View solution

Q. To provide generalization capability to a network, what should be done?

View solution

Q. Does an approximate system produce strictly an interpolated output?

View solution

Q. The nature of mapping problem decides?

View solution

Q. How is hard learning problem solved?

View solution

Q. The number of units in hidden layers depends on?

View solution

Q. From given input-output pairs pattern recognition model should capture characteristics of the system?

View solution

Q. Let a(l), b(l) represent in input-output pairs, where “l” varies in natural range of no.s, then if a(l)=b(l)?

View solution

Q. Let a(l), b(l) represent in input-output pairs, where “l” varies in natural range of no.s, then if a(l)=!b(l)?

View solution

Q. The recalled output in pattern association problem depends on?

View solution

Q. If a(l) gives output b(l) and a’=a(l)+m,where m is small quantity and if a’ gives ouput b(l) then?

View solution

Q. If a(l) gives output b(l) and a’=a(l)+m,where m is small quantity and if a’ gives ouput b(l)+n then?

View solution

Q. Can system be both interpolative and accretive at same time?

View solution

Q. What are 3 basic types of neural nets that form basic functional units?

i)feedforward
ii) loop
iii) recurrent
iv) feedback
v) combination of feed forward and back

View solution

Q. Feedback networks are used for autoassociation and pattern storage?

View solution