1. Delta learning is of unsupervised type?
a) yes
b) no
Explanation: Change in weight is based on the error between the desired & the actual output values for a given input.
2. widrow & hoff learning law is special case of?
a) hebb learning law
b) perceptron learning law
c) delta learning law
d) none of the mentioned
Explanation: Output function in this law is assumed to be linear , all other things same
3. What’s the other name of widrow & hoff learning law?
a) Hebb
b) LMS
c) MMS
d) None of the mentioned
Explanation: LMS, least mean square. Change in weight is made proportional to negative gradient of error & due to linearity of output function
4. 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)) aj
Explanation: Perceptron learning law is supervised, nonlinear type of learning.
5. Correlation learning law is special case of?
a) Hebb learning law
b) Perceptron learning law
c) Delta learning law
d) LMS learning law
Explanation: Since in hebb is replaced by bi(target output) in correlation
6. Correlation learning law is what type of learning?
a) supervised
b) unsupervised
c) either supervised or unsupervised
d) both supervised or unsupervised
Explanation: Supervised, since depends on target output
7. 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 aj
Explanation: Correlation learning law depends on target output(bi)
8. 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 all
Explanation: The unit which gives maximum output, weight is adjusted for that unit
9. 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 identified
Explanation: Follows from basic definition of instar learning law
10. Is instar a case of supervised learning?
a) yes
b) no
Explanation: Since weight adjustment don’t depend on target output, it is unsupervised learning.