CS7643 – Deep Learning Quiz 4: Comprehensive
Actual Exam (100 Questions with Answers and
100%CORRET ANSWERs)
Overview:
This exam is a full-length, 100-question practice test designed to evaluate a student’s
understanding of graduate-level deep learning concepts. It covers core topics including:
• Neural Network Architectures: Feedforward (MLP), Convolutional (CNN), Recurrent
(RNN), LSTM, and GRU networks.
• Activation Functions: ReLU, Leaky ReLU, Sigmoid, Tanh, and Softmax, including their
properties and derivatives.
• Optimization Methods: SGD, Momentum, RMSProp, Adam, learning rate adjustments,
and adaptive optimization techniques.
• Regularization and Stabilization: Dropout, L1/L2 weight penalties, Batch
Normalization, weight initialization (Xavier/He), and gradient clipping.
• Gradient Challenges: Vanishing and exploding gradients, and techniques such as
residual connections to address them.
• Loss Functions: Cross-entropy, MSE, and Hinge loss for classification and regression
tasks.
• Practical Applications: Forward/backward pass calculations, parameter counting, and
PyTorch implementation examples.
Each question includes answers in bold and 100%CORRET ANSWERs, making this practice
exam an excellent tool for reviewing concepts, identifying knowledge gaps, and preparing for
real assessments in CS7643 Deep Learning.
1. Which of the following is NOT a property of ReLU?
A. Non-linear
B. Unbounded above
C. Smooth and differentiable everywhere
D. Encourages sparsity
100%CORRET ANSWER: ReLU is non-linear and unbounded above; it zeros
out negatives (sparse activations) but is not differentiable at 0.
,2. In batch normalization, the γ and β parameters are used to:
A. Normalize inputs to zero mean and unit variance
B. Scale and shift normalized inputs
C. Reduce overfitting directly
D. Speed up gradient computation
100%CORRET ANSWER: γ and β allow the network to restore representation
flexibility after normalization.
3. Adam optimizer combines:
A. SGD and momentum
B. RMSProp only
C. Momentum and adaptive learning rates
D. L2 regularization
100%CORRET ANSWER: Adam uses first-moment (momentum) and second-
moment (RMSProplike) estimates.
4. Dropout primarily helps:
A. Accelerate training
B. Reduce overfitting
C. Improve ReLU performance
D. Initialize weights
100%CORRET ANSWER: Randomly zeroes activations during training to
prevent co-adaptation.
5. The standard loss for multi-class classification is:
A. MSE
B. Cross-entropy
C. Hinge loss
D. KL divergence
,100%CORRET ANSWER: Cross-entropy compares predicted probabilities with
one-hot labels.
6. Vanishing gradients in RNNs lead to:
A. Faster training
B. Inability to learn long-term dependencies
C. Overfitting
D. Weight explosion
100%CORRET ANSWER: Multiplying many small derivatives reduces gradient
magnitude over time.
7. Key advantage of LSTM over vanilla RNN:
A. Faster
B. Fewer parameters
C. Capture long-term dependencies
D. Simpler architecture
100%CORRET ANSWER: LSTM gates preserve gradients and enable learning
across long sequences.
8. Sigmoid activation is used in:
A. Hidden layers of CNNs
B. ReLU replacement
C. Binary classification output
D. Softmax replacement
100%CORRET ANSWER: Sigmoid maps output to (0,1) for probability
interpretation.
9. Xavier initialization aims to:
A. Set all weights to zero
Rationale:
, B. Keep activations’ variance stable across layers
C. Prevent overfitting
D. Speed up ReLU convergence
Balances signal variance for both forward and backward passes.
10. Convolutional layers:
A. Increase parameters compared to fully connected
B. Exploit spatial locality and share parameters
C. Cannot handle variable input sizes
D. Require flattened inputs
100%CORRET ANSWER: Filters reduce parameters and utilize spatial
correlation.
11. Momentum in gradient descent:
A. Reduces learning rate
B. Accelerates updates along consistent directions
C. Prevents overfitting
D. Normalizes gradients
100%CORRET ANSWER: Accumulates past gradients to smooth updates.
12. L2 regularization penalizes:
A. Sparsity
B. Large weights
C. Activations
D. Gradient variance
100%CORRET ANSWER: Reduces overfitting by encouraging smaller weight
magnitudes.
13. Softmax activation:
A. Normalizes weights
B. Zeroes negative values
Actual Exam (100 Questions with Answers and
100%CORRET ANSWERs)
Overview:
This exam is a full-length, 100-question practice test designed to evaluate a student’s
understanding of graduate-level deep learning concepts. It covers core topics including:
• Neural Network Architectures: Feedforward (MLP), Convolutional (CNN), Recurrent
(RNN), LSTM, and GRU networks.
• Activation Functions: ReLU, Leaky ReLU, Sigmoid, Tanh, and Softmax, including their
properties and derivatives.
• Optimization Methods: SGD, Momentum, RMSProp, Adam, learning rate adjustments,
and adaptive optimization techniques.
• Regularization and Stabilization: Dropout, L1/L2 weight penalties, Batch
Normalization, weight initialization (Xavier/He), and gradient clipping.
• Gradient Challenges: Vanishing and exploding gradients, and techniques such as
residual connections to address them.
• Loss Functions: Cross-entropy, MSE, and Hinge loss for classification and regression
tasks.
• Practical Applications: Forward/backward pass calculations, parameter counting, and
PyTorch implementation examples.
Each question includes answers in bold and 100%CORRET ANSWERs, making this practice
exam an excellent tool for reviewing concepts, identifying knowledge gaps, and preparing for
real assessments in CS7643 Deep Learning.
1. Which of the following is NOT a property of ReLU?
A. Non-linear
B. Unbounded above
C. Smooth and differentiable everywhere
D. Encourages sparsity
100%CORRET ANSWER: ReLU is non-linear and unbounded above; it zeros
out negatives (sparse activations) but is not differentiable at 0.
,2. In batch normalization, the γ and β parameters are used to:
A. Normalize inputs to zero mean and unit variance
B. Scale and shift normalized inputs
C. Reduce overfitting directly
D. Speed up gradient computation
100%CORRET ANSWER: γ and β allow the network to restore representation
flexibility after normalization.
3. Adam optimizer combines:
A. SGD and momentum
B. RMSProp only
C. Momentum and adaptive learning rates
D. L2 regularization
100%CORRET ANSWER: Adam uses first-moment (momentum) and second-
moment (RMSProplike) estimates.
4. Dropout primarily helps:
A. Accelerate training
B. Reduce overfitting
C. Improve ReLU performance
D. Initialize weights
100%CORRET ANSWER: Randomly zeroes activations during training to
prevent co-adaptation.
5. The standard loss for multi-class classification is:
A. MSE
B. Cross-entropy
C. Hinge loss
D. KL divergence
,100%CORRET ANSWER: Cross-entropy compares predicted probabilities with
one-hot labels.
6. Vanishing gradients in RNNs lead to:
A. Faster training
B. Inability to learn long-term dependencies
C. Overfitting
D. Weight explosion
100%CORRET ANSWER: Multiplying many small derivatives reduces gradient
magnitude over time.
7. Key advantage of LSTM over vanilla RNN:
A. Faster
B. Fewer parameters
C. Capture long-term dependencies
D. Simpler architecture
100%CORRET ANSWER: LSTM gates preserve gradients and enable learning
across long sequences.
8. Sigmoid activation is used in:
A. Hidden layers of CNNs
B. ReLU replacement
C. Binary classification output
D. Softmax replacement
100%CORRET ANSWER: Sigmoid maps output to (0,1) for probability
interpretation.
9. Xavier initialization aims to:
A. Set all weights to zero
Rationale:
, B. Keep activations’ variance stable across layers
C. Prevent overfitting
D. Speed up ReLU convergence
Balances signal variance for both forward and backward passes.
10. Convolutional layers:
A. Increase parameters compared to fully connected
B. Exploit spatial locality and share parameters
C. Cannot handle variable input sizes
D. Require flattened inputs
100%CORRET ANSWER: Filters reduce parameters and utilize spatial
correlation.
11. Momentum in gradient descent:
A. Reduces learning rate
B. Accelerates updates along consistent directions
C. Prevents overfitting
D. Normalizes gradients
100%CORRET ANSWER: Accumulates past gradients to smooth updates.
12. L2 regularization penalizes:
A. Sparsity
B. Large weights
C. Activations
D. Gradient variance
100%CORRET ANSWER: Reduces overfitting by encouraging smaller weight
magnitudes.
13. Softmax activation:
A. Normalizes weights
B. Zeroes negative values
