Artificial Intelligence - Artificial Neural Networks

Avatto > > UGC NET COMPUTER SCIENCE > > PRACTICE QUESTIONS > > Artificial Intelligence > > Artificial Neural Networks

11. What would be a correct option for weight W [W0 ,W1 ,W2 ], so that the following sigmoid unit will function as an AND gate?

What would be a correct option

  • Option : D
  • Explanation : Consider the weights to be [-10,9,9],
    Then,
    AND function,
    -10 * 1+9 * x1+9 * x2
    9x1 + 9x2 - 10
    If x1 and x2 are equal to 1, the output is also equal to 1.
    Hence, (D) [-10,9,9] is the answer.
Cancel reply

Your email address will not be published. Required fields are marked *


Cancel reply

Your email address will not be published. Required fields are marked *


12. Which of the following is true?

Cancel reply

Your email address will not be published. Required fields are marked *


Cancel reply

Your email address will not be published. Required fields are marked *


13. In a neural network, which one of the following techniques is NOT useful to reduce overfitting?

Cancel reply

Your email address will not be published. Required fields are marked *


Cancel reply

Your email address will not be published. Required fields are marked *


14. For an image recognition problem (such as recognizing a cat in a photo), which architecture of neural network has been found to be better suited for the tasks?

Cancel reply

Your email address will not be published. Required fields are marked *


Cancel reply

Your email address will not be published. Required fields are marked *


15. In training a batch neural network, after running the first few epochs, you notice that the loss does not decrease. The reasons for this could be
1. The learning rate is low.
2. The neural net is stuck in local minima
3. The neural net has too many units in the hidden layer

Cancel reply

Your email address will not be published. Required fields are marked *


Cancel reply

Your email address will not be published. Required fields are marked *