VIVA BP-ANN B-2

1. What do the gradients of backpropagation compute?

•  a. Profit Function

•  b. Loss Function

•  c. Maximization Function

• d. Negative Function

2. Which rule is followed by the Backpropagation algorithm to tune weights?

•  a. Static Rule

•  b. Dynamic Rule

•  c. Delta Rule

• d. None of the above

3. What determines the influence of gradient in backpropagation?

• a. Number of Inputs

•  b. Number of Outputs

• c. Learning Rate

•  d. Number of Intermediate Stages

4. In backpropagation chain rule is followed to determine ?

• a. Gradients

• b. Number of Inputs

• c. Number of Outputs

•   d. Number of Intermediate Stages

5. Backpropagation algorithm is highly sensitive for ?

• a. Noise Less Data

•  b. Data Irregularities

•  c. d & b

• d. Noisy Data

6. What is true regarding backpropagation rule?

• a) it is also called generalized delta rule

• b) error in output is propagated backwards only to determine weight updates

• c) there is no feedback of signal at any stage
  
  

• d) all of the mentioned

7. What are general limitations of back propagation rule?

• a) local minima problem

• b) slow convergence

• c) both a and b

• d) none of the above

8. Backpropagation is capable of handling large learning problems.

• a. TRUE

• b. FALSE

9. A differentiable activation function makes the function computed by a neural network differentiable and the back propagation algorithm is applicable to it.

• a. FALSE

• b. TRUE

10. What of the following is true regarding backpropagation rule?

• (A) Hidden layers output is not all important, they are only meant for supporting input and output layers
  
  

• (B) Actual output is determined by computing the outputs of units for each hidden layer
  
  

• (C) It is a feedback neural network
  
  

• (D) None of the above