Are you looking for NPTEL Introduction to Machine Learning Assignment Week 5 Answers? If yes, you will find the answers to the questions asked in the NPTEL Introduction to Machine Learning quiz exam here. If you are preparing for this exam this article will help you in finding the latest and updated answers.

There is a total of 11 questions related to Neural Networks – Introduction, Early Models, Perceptron Learning, Backpropagation, Initialization, Training & Validation, Parameter Estimation – MLE, MAP, Bayesian Estimation. The correct answers are marked in Green Color with a tick sign.

Note: If the questions in the exam is not same/changed please share them with us, so that we update with the latest questions & answers

NPTEL Introduction to Machine Learning Assignment Week 5 Answers

1. For training a binary classification model with three independent variables, you choose to use neural networks. You apply one hidden layer with three neurons. What are the number of parameters to be estimated? (Consider the bias term as a parameter)

  1. 16
  2. 021
  3. 34= 81
  4. 43 =81
  5. 12
  6. 4
  7. None of these

2. Suppose the marks obtained by randomly sampled students follow a normal distribution with unknown µ. A random sample of 5 marks are 30, 50, 69, 2 and 99. Using the given samples find the maximum likelihood estimate for the mean.

  1. 54.2
  2. 67.75
  3. 50
  4. Information not sufficient for estimation

3. You are given the following neural networks which take two binary valued inputs x1, x2 ∈ {0,1} and the activation function is the threshold function (h(x) = 1 if x > 0; 0 otherwise). Which of the following logical functions does it compute?

Which of the following logical functions does it compute?
  1. OR
  2. AND
  3. NAND
  4. None of the above.

4. Using the notations used in class, evaluate the value of the neural network with a 3-3-1 architecture (2-dimensional input with 1 node for the bias term in both the layers). The parameters are as follows

α = [1  0.2  0.4]
    [-1  0.8  0.5]

β = [0.3  0.4  0.5]

Using sigmoid function as the activation functions at both the layers, the output of the network for an input of (0.8, 0.7) will be

  1. 0.6710
  2. 0.9617
  3. 0.6948
  4. 0.7052
  5. None of these

5. Which of the following statements is false

  1. The chances of overfitting decrease with Increasing the number of hidden nodes and increasing the number of hidden layers.
  2. A neural network with one hidden layer can represent any Boolean function given sufficient number of hidden units and appropriate activation functions.
  3. Two hidden layer neural networks can represent any continuous functions (within a tolerance) as long as the number of hidden units is sufficient and appropriate activation functions used.

6. Consider the function f1(x) = eα0 + αx / 1+ eα0+αx and f2(x) = eβ0+βx / 1+eβ0+βx shown in the figure below:

Consider the function f1(x) = eα0 + αx / 1+ eα0+αx and f2(x) = eβ0+βx / 1+eβ0+βx shown in the figure below:

Which of the following is correct?

  1. 0 < β < α
  2. 0 < α < β
  3. α < ß < 0
  4. β < α < 0

7. We have a function which takes a two-dimensional input x = (x1, x2) and has two parameters w= (ω1, ω2) given by

f(x, ω)= σ(σ(x1ω)ω2 + x2) where σ(x) = 1 / 1+e-x. We use backpropagation to estimate the right parameter values. We start by setting both the parameters to 0.
Assume that we are given a training point x2=1, x1 = 0, y= 5. Given this information ǝf / ǝω2?

  1. 0.150
  2. -0.25
  3. 0.125
  4. 0.098
  5. None of these

8. If the leaming rate is 0.5, what will be the value of w after one update using backpropagation algorithm

  1. 0.4197
  2. -0.4197
  3. 0.5625
  4. 0.5625

9 Which of the following are true when comparing ANNs and SVMs?

  1. ANN error surface has multiple local minima while SVM error surface has only one minima
  2. After training, an ANN might land on a different minimum each time, when initialized with random weights during each run.
  3. As shown for Perceptron, there are some classes of functions that cannot be leant by an ANN. An SVM can lean a hyperplane for any kind of distribution.
  4. In training. ANN’s error surface is navigated using a gradient descent technique while SVM’s error surface is navigated using convex optimization solvers.
NPTEL Introduction to Machine Learning Assignment Answers

FAQ

What is NPTEL Introduction to Machine Learning?

NPTEL Introduction to Machine Learning Course is an online free course by IIT Madras that has been developed by Prof. Balaraman Ravindran. The main aim of this course is to provide the basic concepts of machine learning from a mathematically well-motivated perspective.

Are These Answers Correct?

Yes, all these answers are 100% correct.

Are These Answers Updated?

Yes, these answers are up to date with the latest questions.

Will I Get a Certificate?

Yes, you will get a certificate but it costs ₹1000 exam fee.

Wrap Up

I hope now you know all the NPTEL Introduction to Machine Learning Assignment Week 5 Answers. If this article helped you find the NPTEL Introduction to Machine Learning Course Answer don’t forget to share it with your friends who are looking for NPTEL Introduction to Machine Learning Assignment Answers.

Disclaimer: These Answers are only for educational purposes so please don’t use them for any cheating purposes. We urge you to do assignments on your own.

Leave a Reply

Your email address will not be published.