These are NPTEL Deep Learning Week 4 Assignment 4 Answers
Q1. A given cost function is of the form J(0) = 202-40+2? What is the weight update rule for gradient descent optimization at step t+1? Consider, a=0.01 to be the learning rate. a. 8t+1=0 -0.01 (201) b. 0+1 = 0 + 0.01 (20) c. Ot+1=0t (201) d. 0+1 = 0 0.04(0 – 1)
Answer: d. 0+1 = 0 0.04(0 – 1)
Q2. Which of the following activation function leads to sparse activation maps? a. Sigmoid b. Tanh c. Linear d. ReLU
Answer: d. ReLU
These are NPTEL Deep Learning Week 4 Assignment 4 Answers
Q3. If yi is the ground truth label for ith training data, p, is the predicted label. For a binary class classification, which of the following is a feasible loss function for training a neural net. C is the number of training data a. -E-1 yi log p₁ – E-1(1 – y₁) log(1 – p₁) b. -E1Y₁ log p₁ – E-₁ yi log(1 – pt) гс c. E 1 yi log(1 – P₁) – Σ₁(1 – y₁) log(p;) d. E (1-y₁) log p₁ – E-₁ yi log(1 – p₁)
Answer: a. -E-1 yi log p₁ – E-1(1 – y₁) log(1 – p₁)
Q4. Which logic function cannot be performed using a single-layered Neural Network? a. AND b. OR c. XOR d. All
Answer: c. XOR
These are NPTEL Deep Learning Week 4 Assignment 4 Answers
Q5. Which of the following options closely relate to the following graph? Green cross are the samples of Class-A while mustard rings are samples of Class-B and the red line is the separating line between the two class.
a. High Bias b. Zero Bias c. Zero Bias and High Variance d. Zero Bias and Zero Variance
Answer: a. High Bias
Q6. Which of the following statement is true? a. L2 regularization lead to sparse activation maps b. L1 regularization lead to sparse activation maps c. Some of the weights are squashed to zero in L2 regularization d. L2 regularization is also known as Lasso
Answer: b. L1 regularization lead to sparse activation maps
These are NPTEL Deep Learning Week 4 Assignment 4 Answers
Q7. Which among the following options give the range for a tanh function? a. -1 to 1 b. -1 to 0 c. 0 to 1 d. 0 to infinity
Answer: a. -1 to 1
These are NPTEL Deep Learning Week 4 Assignment 4 Answers
Q8. Consider the following neural network shown in the figure with inputs x1, x2 and output Y. The inputs take the values x₁, x₁ € {0,1}. The logical operation performed by the network is
a. AND b. OR c. XOR d. NOR
Answer: d. NOR
These are NPTEL Deep Learning Week 4 Assignment 4 Answers
Q9. When is gradient descent algorithm certain to find a global minima? a. For convex cost plot b. For concave cost plot c. For union of 2 convex cost plot d. For union of 2 concave cost plot
Answer: a. For convex cost plot
These are NPTEL Deep Learning Week 4 Assignment 4 Answers
Q10. Let X=[-1, 0, 3, 5] be the the input of ith layer of a neural network. On this, we want to apply softmax function. What should be the output of it? a. [0.368, 1, 20.09, 148.41] b. [0.002, 0.006, 0.118,0.874] c. [0.3, 0.05,0.6,0.05] d. [0.04,0,0.06,0.9]
