Question 46 NAT · 1.0 marks
What is the cost of the optimal tour?
NO SPACES, TABS, DOTS, BRACKETS OR EXTRANEOUS CHARACTERS.
Answer format: 17
A published solution is not available for this question yet.
Deep Learning · Quiz 2 · Sep 2023
Deep Learning · Quiz 2 · Sep 2023
← Course papers · Start practice / exam
Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.
0 / 18 published solutions
Question 48 MCQ · 2.0 marks
The statement that the bias correction in ADAM optimizer is an absolute requirement for it to
converge to a local minimum is
TRUE
FALSE
A published solution is not available for this question yet.
Question 49 MSQ · 5.0 marks
the training error becomes zero
the testing error becomes zero
both the bias and variance of the model become zero
model has zero bias and non-zero variance
model has non-zero bias and non-zero variance
A published solution is not available for this question yet.
Question 50 MSQ · 5.0 marks
A published solution is not available for this question yet.
Question 51 MSQ · 3.0 marks
Which of the following optimization algorithms adapts the learning rate based on the current
gradient and history of gradients?
Gradient Descent with exponentially decaying learning rate
RMSProp
Nesterov Accelerated Gradient Descent with step decay
ADAM
Ada-Delta
A published solution is not available for this question yet.
Question 52 MSQ · 3.0 marks
In general, applying regularization to an over-fitted deep learning model
decreases the training error of the over-parameterized model
increases the training error of the over-parameterized model
reduces the testing error of the over-parameterized model
improves the generalization ability of the over-parameterized model
A published solution is not available for this question yet.
Question 53 MSQ · 4.0 marks
Assume a team has trained a CNN model for image classification. They observed that the model
was performing poorly (that is, both training and testing errors were high). Which of the following
would be a more appropriate measure that might improve the performance of the model?
apply data augmentation techniques
inject noise at the input
increase the model complexity by adding more layers (therefore, more
parameters)
decrease the model complexity by removing a few layers
apply L2 regularization
A published solution is not available for this question yet.
Question 54 MSQ · 4.0 marks
A published solution is not available for this question yet.
Question 55 MCQ · 2.0 marks
Based on the above data, answer the given subquestions.
The statement that,“ The gradient of the weight w changes slowly as compared to the gradient of
the bias b if we move on the contours of the loss surface in the direction parallel to the weight.” is
TRUE
FALSE
A published solution is not available for this question yet.
Question 56 MCQ · 2.0 marks
Based on the above data, answer the given subquestions.
The statement that,“the gradient of the bias b changes rapidly as compared to the gradient of the
weight w if we move on the contours of the loss surface in the direction perpendicular to the
weight” is
TRUE
FALSE
A published solution is not available for this question yet.
Question 57 MCQ · 2.0 marks
Based on the above data, answer the given subquestions.
The statement that,“The algorithm converged to the (local or global) minimum after 500
iterations” is
TRUE
FALSE
A published solution is not available for this question yet.
Question 58 SHORT_TEXT · 2.0 marks
Based on the above data, answer the given subquestions.
The dimension of C1 = 101 × 101 × 100. Suppose we use 25 kernels (filters) of shape 3 × 3, with
stride 1 and no zero padding, to generate the convolution layer 2. Then, enter the number of
parameters (excluding bias) in the convolution layer-2 (If your answer is 1050, enter 1050)
A published solution is not available for this question yet.
Question 59 SHORT_TEXT · 2.0 marks
Based on the above data, answer the given subquestions.
We know that the shape of the flattened layer is N × 1. What is the value of N ?(If your answer is
1050,enter 1050)
A published solution is not available for this question yet.
Question 60 SHORT_TEXT · 2.0 marks
Based on the above data, answer the given subquestions.
Suppose we feed in the features F of dimension N × 1 to a fully connected layer with 4 neurons
(assume no bias) with the softmax activation function. How many additional parameters are added
to the network?
A published solution is not available for this question yet.
Question 61 NAT · 3.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 62 NAT · 3.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 63 NAT · 2.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.
Question 64 NAT · 4.0 marks
Based on the above data, answer the given subquestions.
A published solution is not available for this question yet.