These are NPTEL Deep Learning Week 5 Assignment 5 Answers
Q1. The activation function which is not analytically differentiable for all real values of the given input is a. Sigmoid b. Tanh c. RelU d. Both a&b
Answer: c. RelU
Q2. What is the main benefit of stacking multiple layers of neuron with non-linear activation functions over a single layer perceptron? a. Reduces complexity of the network b. Reduce inference time during testing c. Allows to create non-linear decision boundaries d. All of the above
Answer: c. Allows to create non-linear decision boundaries
These are NPTEL Deep Learning Week 5 Assignment 5 Answers
Q3. What will the output from node a3 in the following neural network setup when the inputs are (x1,x2) = (1,1).The activation function used in each of three nodes a,, a, and a; are zero- thresholdingi.e f(x) = 1if x > 0else 0?
a. -1 b. 0 c. 1 d. 0.5
Answer: c. 1
Q4. Suppose a neural network has 3 input 3 nodes, x, y, z. There are 2 neurons, Qand F. Q=4x +y and F = Q * z2. What is the gradient of F with respect to x, y and z? Assume, (x, y, z) = (-2, 5, -4). a. (64,16, 24) b. (-24,-4,16) c. (4,4,-13) d. (13,13,24)
Answer: a. (64,16, 24)
These are NPTEL Deep Learning Week 5 Assignment 5 Answers
Q5. Which of the following properties, if present in an activation function CANNOT be used in a neural network? a. The function is periodic b. The function is monotonic c. The function is unbounded d. Bothaandb
Q6. For a binary classification setting. what if the probability of belonging to class = +1 is 0.67 the probability of belonging to class= -1? a. 0 b. 033 c. 0.67*0.33 d 1- (067 * 067)
Answer: b. 033
These are NPTEL Deep Learning Week 5 Assignment 5 Answers
Q7. Suppose a fully-connected neural network has a single hidden layer with 10 nodes. The input is represented by a 5D feature vector and the number of classes is 3. Calculate the number of 3 parameters of the network. Consider there are NO bias nodes in the network? a. 80 b. 75 c. 78 d. 120
Answer: a. 80
These are NPTEL Deep Learning Week 5 Assignment 5 Answers
Q8. For a 2-class classification problem, what is the minimum number of nodes required for the output layer of a multi-layered neural network? a. 2 b. 1 c. 3 d. None of the above
Answer: b. 1
These are NPTEL Deep Learning Week 5 Assignment 5 Answers
Q9. Suppose the input layer of a fully-connected neural network has 4 nodes. The value of a node in the first hidden layer before applying sigmoid nonlinearity is V. Now, each of the input layer’s nodes are called up by 8 times. What will be the value of that neuron with the updated input layer? a. 8v b. 4v c. 32v d. Remain same since scaling of input layers does not affect the hidden layers
Answer: a. 8v
These are NPTEL Deep Learning Week 5 Assignment 5 Answers
Q10. Which of the following are potential benefits of using ReLU activation over sigmoid activation? a. Relu helps in creating dense (most of the neurons are active) representations b. Relu helps in creating sparse (most of the neurons are non-active) representations c. Relu helps in mitigating vanishing gradient effect d. Both (b) and (c)
