Practice Library
All MCQs
Browse exam-wise, subject-wise, and country-wise MCQs with explanations.
Choose an option to check your answer.
A.
A multilayer perceptron uses layers of neurons with nonlinear activations
B.
An MLP is a database indexing method
C.
An MLP has no trainable weights
D.
An MLP can only process images
Show Answer
Correct Answer: A. A multilayer perceptron uses layers of neurons with nonlinear activations
Explanation:
The correct answer is a multilayer perceptron uses layers of neurons with nonlinear activations. This matches the Deep Learning course topic: MLP.
Choose an option to check your answer.
A.
Underfitting means perfect training accuracy
B.
Underfitting is solved by removing all features
C.
Underfitting is the same as data leakage
D.
Underfitting occurs when a model is too simple to capture important patterns
Show Answer
Correct Answer: D. Underfitting occurs when a model is too simple to capture important patterns
Explanation:
The correct answer is underfitting occurs when a model is too simple to capture important patterns. This matches the Deep Learning course topic: Underfitting.
Choose an option to check your answer.
A.
Overfitting always improves test accuracy
B.
Overfitting occurs only in linear regression
C.
Overfitting occurs when a model learns noise or specific training patterns too strongly
D.
Overfitting means the model is too simple for the data
Show Answer
Correct Answer: C. Overfitting occurs when a model learns noise or specific training patterns too strongly
Explanation:
The correct answer is overfitting occurs when a model learns noise or specific training patterns too strongly. This matches the Deep Learning course topic: Overfitting.
Choose an option to check your answer.
A.
Generalization can only be measured on training loss
B.
Generalization is the ability to perform well on unseen examples
C.
Generalization means memorizing every training sample
D.
Generalization is unrelated to overfitting
Show Answer
Correct Answer: B. Generalization is the ability to perform well on unseen examples
Explanation:
The correct answer is generalization is the ability to perform well on unseen examples. This matches the Deep Learning course topic: Generalization.
Choose an option to check your answer.
A.
A validation set supports model selection and hyperparameter tuning
B.
A validation set is always larger than the training set
C.
A validation set replaces the loss function
D.
A validation set stores GPU kernels
Show Answer
Correct Answer: A. A validation set supports model selection and hyperparameter tuning
Explanation:
The correct answer is a validation set supports model selection and hyperparameter tuning. This matches the Deep Learning course topic: Validation set.
Choose an option to check your answer.
A.
A test set is used to update weights every epoch
B.
A test set should be identical to the training set
C.
A test set is used for data normalization only
D.
A test set estimates performance on unseen data
Show Answer
Correct Answer: D. A test set estimates performance on unseen data
Explanation:
The correct answer is a test set estimates performance on unseen data. This matches the Deep Learning course topic: Test set.
Choose an option to check your answer.
A.
A training set contains no labels in supervised learning
B.
A training set is the final exam dataset
C.
A training set is used to fit model parameters
D.
A training set is used only after deployment
Show Answer
Correct Answer: C. A training set is used to fit model parameters
Explanation:
The correct answer is a training set is used to fit model parameters. This matches the Deep Learning course topic: Training set.
Choose an option to check your answer.
A.
Shallow learning cannot perform classification
B.
Deep models usually contain multiple hidden layers
C.
Shallow models always contain more layers than deep models
D.
Deep learning removes the need for training data
Show Answer
Correct Answer: B. Deep models usually contain multiple hidden layers
Explanation:
The correct answer is deep models usually contain multiple hidden layers. This matches the Deep Learning course topic: Shallow vs deep learning.
Choose an option to check your answer.
A.
Deep learning learns layered representations from raw data
B.
It relies only on one manually written rule
C.
It can never use gradient descent
D.
It only works with tabular data
Show Answer
Correct Answer: A. Deep learning learns layered representations from raw data
Explanation:
The correct answer is deep learning learns layered representations from raw data. This matches the Deep Learning course topic: Basics of deep learning.
Choose an option to check your answer.
A.
adding stack symbols to a DFA
B.
making a language non-regular
C.
reducing a DFA to an equivalent DFA with fewer states where possible
D.
converting every CFG into a TM
Show Answer
Correct Answer: C. reducing a DFA to an equivalent DFA with fewer states where possible
Explanation:
The suitable explanation is reducing a DFA to an equivalent DFA with fewer states where possible.
Choose an option to check your answer.
A.
adding stack symbols to a DFA
B.
reducing a DFA to an equivalent DFA with fewer states where possible
C.
making a language non-regular
D.
converting every CFG into a TM
Show Answer
Correct Answer: B. reducing a DFA to an equivalent DFA with fewer states where possible
Explanation:
In this course context, state minimization means reducing a DFA to an equivalent DFA with fewer states where possible.
Choose an option to check your answer.
A.
adding stack symbols to a DFA
B.
converting every CFG into a TM
C.
reducing a DFA to an equivalent DFA with fewer states where possible
D.
making a language non-regular
Show Answer
Correct Answer: C. reducing a DFA to an equivalent DFA with fewer states where possible
Explanation:
state minimization is correctly described as reducing a DFA to an equivalent DFA with fewer states where possible.
