1.Continuous perceptron learning is also known as delta learning?
a) yes
b) no
Explanation: Follows from basic definition of delta learning
2. Widrows LMS algorithm is also based on error correction learning?
a) yes
b) no
Explanation: It uses the instantaneous squared error between desired & actual output of unit
3. Error correction learning is type of?
a) supervised learning
b) unsupervised learning
c) can be supervised or unsupervised
d) none of the mentioned
Explanation: Since desired output for an input is known
4. Error correction learning is like learning with teacher?
a) yes
b) no
Explanation: Since desired output for an input is known.
5. What is reinforcement learning?
a) learning is based on evaluative signal
b) learning is based o desired output for an input
c) learning is based on both desired output & evaluative signal
d) none of the mentioned
Explanation: Reinforcement learning is based on evaluative signal.
6. Stability refers to adjustment in behaviour of weights during learning?
a) yes
b) no
Explanation: Stability refers to equilibrium behaviour of activation state
7. Convergence refers to equilibrium behaviour of activation state?
a) yes
b) no
Explanation:Convergence refers to adjustment in behaviour of weights during learning
8. What leads to minimization of error between the desired & actual outputs?
a) stability
b) convergence
c) either stability or convergence
d) none of the mentioned
Explanation:Convergence is responsible for minimization of error between the desired & actual outputs
9. Stability is minimization of error between the desired & actual outputs?
a) yes
b) no
Explanation: Convergence is minimization of error between the desired & actual outputs.
10. How many trajectories may terminate at same equilibrium state?
a) 1
b) 2
c) many
d) none
Explanation: There may be several trajectories that may settle to same equilibrium state.