adplus-dvertising
frame-decoration

Question

Generalization feature of a multilayer feedforward network depends on factors?

a.

architectural details

b.

learning rate parameter

c.

training samples

d.

all of the mentioned

Posted under Neural Networks

Answer: (a).architectural details

Engage with the Community - Add Your Comment

Confused About the Answer? Ask for Details Here.

Know the Explanation? Add it Here.

Q. Generalization feature of a multilayer feedforward network depends on factors?

Similar Questions

Discover Related MCQs

Q. What is accretive behaviour?

Q. What is Interpolative behaviour?

Q. Does pattern association involves non linear units in feedforward neural network?

Q. What is the feature that doesn’t belongs to pattern classification in feeddorward neural networks?

Q. What is the feature that doesn’t belongs to pattern mapping in feeddorward neural networks?

Q. In determination of weights by learning, for orthogonal input vectors what kind of learning should be employed?

Q. In determination of weights by learning, for linear input vectors what kind of learning should be employed?

Q. In determination of weights by learning, for noisy input vectors what kind of learning should be employed?

Q. What are the features that can be accomplished using affine transformations?

Q. What is the features that cannot be accomplished earlier without affine transformations?

Q. What are affine transformations?

Q. Can a artificial neural network capture association if input patterns is greater then dimensionality of input vectors?

Q. By using only linear processing units in output layer, can a artificial neural network capture association if input patterns is greater then dimensionality of input vectors?

Q. Number of output cases depends on what factor?

Q. For noisy input vectors, Hebb methodology of learning can be employed?

Q. What is the objective of perceptron learning?

Q. On what factor the number of outputs depends?

Q. In perceptron learning, what happens when input vector is correctly classified?

Q. When two classes can be separated by a separate line, they are known as?

Q. If two classes are linearly inseparable, can perceptron convergence theorem be applied?