ITCS 1213 UNCC FINAL EXAM QUESTIONS WITH
COMPLETE SOLUTION GRADED A+
/1. PCA identifies the axis that accounts for the __________ in the training set. -
Answer-largest amount of variance
/.2. What is the standard matrix factorization technique that can decompose the training
set matrix into a dot product of 3 matrices, with the latter of these matrices containing
the principal components? - Answer-Singular Value Decomposition (SVD)
/.True or False.....3. Numerical differentiation has a high accuracy. - Answer-False, it
has low accuracy and is difficult to implement
/.4. What method is called to restore a previously saved model? - Answer-restore()
/.5. What is the derivative of the step function at 0? - Answer-undefined
/.6. What is the output range for a hyperbolic tangent activation function (tanh(z) =
2*sigma(2*zeta) - 1)? - Answer--1 to 1
/.7. The ________ activation function involves α (hyperparameter that determines how
much the function "leaks") being learned during training instead of being a
hyperparameter. - Answer-parametric leaky ReLU
/.8. _______ regularization technique involves each neuron having a probability p of
being temporarily "dropped" - Answer-Dropout
/.9. What function is NOT used to make a pooling layer for a CNN?
A) max_pool()
B) avg_pool()
C) min_pool()
D) all of these are used - Answer-C) Min_pool()
/.10. Autoencoders typically have a symmetrical neural network structure...True or
False? - Answer-True
/.True or False....CNN's are able to generalize much better that DNN's for image
processing tasks such as classification using fewer training examples. - Answer-True
/.12. A ___________________ normalization layer makes the neurons that most
strongly activate inhibit neurons at the same location but in neighboring feature maps. -
Answer-local response
, /.13. In Scikit-Learn's GridSearchCV, all you need to do is tell it which
________________
you want it to experiment with, and what values to try out, and it will evaluate all the
possible combinations of _______________ values, using cross-validation. - Answer-
hyperparameters, hyperparameter
/.14. A CNN is faster to train than a DNN because of the following reason.
1. Partially Connected Layers.
2. Reusability of weights.
3. Both A and B. - Answer-C) Both A and B
/.15. What type of TensorFLow optimizer may be used to compute an optimal gradient?
A) LossOptimizer() B) GradientDescentOptimizer()
C)ErrorOptimizer() D)SquaredErrorOptimizer - Answer-B) Gradient Descent Optimizer
/.How is a perceptron trained? - Answer-Perceptrons are trained based on an algorithm
that considers the error made by the network. The connections that lead to the wrong
output are neglected and not reinforced.
/.17. How does TensorFlow treat dependencies in graph nodes? - Answer-In the case of
graph nodes TensorFLow will recompute the value of a node even if it has encountered
it previously.
/.18. Building an RNN using __________ instead of __________ offers several
advantages.(State the function names) - Answer-dynamic_rnn(), static_rnn
/.19. Which of the following is an example of a vector-to-sequence RNN:
1. Locating pedestrians in a picture
2. Speech to text.
3. Video captioning.
4. A and C
5. B and C - Answer-Locating pedestrians in a picture.
/.True or False....A classical Perceptron is able to estimate class probabilities. - Answer-
False
/.21. How do you clear all nodes from the default graph?
A) Restart the kernel/shell.
B) Call tf.get_default_graph().clear()
C) Call tf.reset_default_graph()
D) A & B
E) A & C - Answer-Answer:
COMPLETE SOLUTION GRADED A+
/1. PCA identifies the axis that accounts for the __________ in the training set. -
Answer-largest amount of variance
/.2. What is the standard matrix factorization technique that can decompose the training
set matrix into a dot product of 3 matrices, with the latter of these matrices containing
the principal components? - Answer-Singular Value Decomposition (SVD)
/.True or False.....3. Numerical differentiation has a high accuracy. - Answer-False, it
has low accuracy and is difficult to implement
/.4. What method is called to restore a previously saved model? - Answer-restore()
/.5. What is the derivative of the step function at 0? - Answer-undefined
/.6. What is the output range for a hyperbolic tangent activation function (tanh(z) =
2*sigma(2*zeta) - 1)? - Answer--1 to 1
/.7. The ________ activation function involves α (hyperparameter that determines how
much the function "leaks") being learned during training instead of being a
hyperparameter. - Answer-parametric leaky ReLU
/.8. _______ regularization technique involves each neuron having a probability p of
being temporarily "dropped" - Answer-Dropout
/.9. What function is NOT used to make a pooling layer for a CNN?
A) max_pool()
B) avg_pool()
C) min_pool()
D) all of these are used - Answer-C) Min_pool()
/.10. Autoencoders typically have a symmetrical neural network structure...True or
False? - Answer-True
/.True or False....CNN's are able to generalize much better that DNN's for image
processing tasks such as classification using fewer training examples. - Answer-True
/.12. A ___________________ normalization layer makes the neurons that most
strongly activate inhibit neurons at the same location but in neighboring feature maps. -
Answer-local response
, /.13. In Scikit-Learn's GridSearchCV, all you need to do is tell it which
________________
you want it to experiment with, and what values to try out, and it will evaluate all the
possible combinations of _______________ values, using cross-validation. - Answer-
hyperparameters, hyperparameter
/.14. A CNN is faster to train than a DNN because of the following reason.
1. Partially Connected Layers.
2. Reusability of weights.
3. Both A and B. - Answer-C) Both A and B
/.15. What type of TensorFLow optimizer may be used to compute an optimal gradient?
A) LossOptimizer() B) GradientDescentOptimizer()
C)ErrorOptimizer() D)SquaredErrorOptimizer - Answer-B) Gradient Descent Optimizer
/.How is a perceptron trained? - Answer-Perceptrons are trained based on an algorithm
that considers the error made by the network. The connections that lead to the wrong
output are neglected and not reinforced.
/.17. How does TensorFlow treat dependencies in graph nodes? - Answer-In the case of
graph nodes TensorFLow will recompute the value of a node even if it has encountered
it previously.
/.18. Building an RNN using __________ instead of __________ offers several
advantages.(State the function names) - Answer-dynamic_rnn(), static_rnn
/.19. Which of the following is an example of a vector-to-sequence RNN:
1. Locating pedestrians in a picture
2. Speech to text.
3. Video captioning.
4. A and C
5. B and C - Answer-Locating pedestrians in a picture.
/.True or False....A classical Perceptron is able to estimate class probabilities. - Answer-
False
/.21. How do you clear all nodes from the default graph?
A) Restart the kernel/shell.
B) Call tf.get_default_graph().clear()
C) Call tf.reset_default_graph()
D) A & B
E) A & C - Answer-Answer:
