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

Neural Networks - Quiz(MCQ)

all units should be linear

all units should be non â€“ linear

except input layer, all units in other layers should be non â€“ linear

none of the above

Correct Answer : except input layer, all units in other layers should be non â€“ linear

Explanation : To provide generalization capability to a network, except input layer, all units in other layers should be non – linear.

Recently Updated in Neural Networks Questions

A greater value of 'p' the vigilance parameter leads to?

No change

Bigger clusters

Small clusters

None of the above

Correct Answer : Small clusters

Explanation : Input samples associated with same neuron get reduced.

What type of inputs does ART â€“ 1 receives?

binary

bipolar

both bipolar and binary

none of the above

Correct Answer : binary

Explanation : Adaptive resonance theory take care of stability plasticity dilemma.

What does vigilance parameter in ART determines?

Number of desired outputs

Number of possible outputs

Number of acceptable inputs

None of the above

Correct Answer : None of the above

Explanation : Vigilance parameter in ART determines the tolerance of matching process.

New Technologies MCQ's

Machine Learning

Artificial Intelligence