NPTEL Introduction to Machine Learning Assignment 5 Answer

We Discuss About That NPTEL Introduction to Machine Learning Assignment 5 Answer

NPTEL Introduction to Machine Learning Assignment 5 Answer – Here All The Questions and Answers Provided to Help All The Students and NPTEL Candidate as a Reference Purpose, It is Mandetory to Submit Your Weekly Assignment By Your Own Understand Level.

Are you looking for the Assignment Answers to NPTEL Introduction to Machine Learning Assignment 5 Answer? If Yes You are in Our Great Place to Getting Your Solution, This Post Should be help you with the Assignment answer to the National Programme on Technology Enhanced Learning (NPTEL) Course “NPTEL Introduction to Machine Learning Assignment 5 Answer”

NPTEL Introduction to Machine Learning Assignment

Next Week Assignment Answers

CHECK HERE OTHERS NPTEL ASSIGNMENTS ANSWERS 

BELOW YOU CAN GET YOUR NPTEL Introduction to Machine Learning Assignment 5 Answer 2022? :

Answers will be Uploaded Shortly and it will be Notified on Telegram, So JOIN NOW

1 point

If the step size in gradient descent is too large, what can happen?

 Overfitting

 The model will not converge

 We can reach maxima instead of minima

 None of the above

Ans – B

1 point

Recall the XOR(tabulated below) example from class where we did a transformation of features to make it linearly separable. Which of the following transformations can also work?

X‘1=X21,X‘2=X22X′1=X12,X′2=X22

X‘1=1+X1,X‘2=1−X2X′1=1+X1,X′2=1−X2

X‘1=X1X2,X‘2=−X1X2X′1=X1X2,X′2=−X1X2

X‘1=(X1−X2)2,X‘2=(X1+X2)2X′1=(X1−X2)2,X′2=(X1+X2)2

Ans – C

1 point

What is the effect of using activation function f(x)=xf(x)=x for hidden layers in an ANN?

 No effect. It’s as good as any other activation function (sigmoid, tanh etc).

 The ANN is equivalent to doing multi-output linear regression.

 Backpropagation will not work.

 We can model highly complex non-linear functions.

Ans – B

Answers will be Uploaded Shortly and it will be Notified on Telegram, So JOIN NOW

1 point

Which of the following functions can be used on the last layer of an ANN for classification?

 Softmax

 Sigmoid

 Tanh

 Linear

Ans – B,C

1 point

Statement: Threshold function cannot be used as activation function for hidden layers.
Reason: Threshold functions do not introduce non-linearity.

 Statement is true and reason is false.

 Statement is false and reason is true.

 Both are true and the reason explains the statement.

 Both are true and the reason does not explain the statement.

Ans -A

1 point

We use several techniques to ensure the weights of the neural network are small (such as random initialization around 0 or regularisation). What conclusions can we draw if weights of our ANN are high?

 Model has overfitted.

 It was initialized incorrectly.

 At least one of (a) or (b).

 None of the above.

Ans -C

1 point

On different initializations of your neural network, you get significantly different values of loss. What could be the reason for this?

 Overfitting

 Some problem in the architecture

 Incorrect activation function

 Multiple local minima

Ans -A

1 point

The likelihood L(θ|X)L(θ|X) is given by:

P(θ|X)P(θ|X)

P(X|θ)P(X|θ)

P(X).P(θ)P(X).P(θ)

P(θ)P(X)P(θ)P(X)

Ans – B

Answers will be Uploaded Shortly and it will be Notified on Telegram, So JOIN NOW

1 point

You are trying to estimate the probability of it raining today using maximum likelihood estimation. Given that in nn days, it rained nrnr times, what is the probability of it raining today?

nrnnrn

nrnr+nnrnr+n

nnr+nnnr+n

 None of the above.

Ans -A

1 point

Choose the correct statement (multiple may be correct):

 MLE is a special case of MAP when prior is a uniform distribution.

 MLE acts as regularisation for MAP.

 MLE is a special case of MAP when prior is a beta disrubution .

 MAP acts as regularisation for MLE.

Ans -A,D

Yhaa You have done it but next? if YOU Want to your Others NPTEL Introduction to Machine Learning Assignment 5 Answer  Then Follow US HERE and Join Telegram.