Deep Learning | testinflow.com

Semester Exam Deep Learning InternationalMedium

Which statement would be accepted as correct about Underfitting? Use the application-oriented interpretation.

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

Correct Answer: D. Underfitting occurs when a model is too simple to capture important patterns

Semester Exam Deep Learning InternationalEasy

Which statement best describes MLP? Use the application-oriented interpretation.

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

Correct Answer: A. A multilayer perceptron uses layers of neurons with nonlinear activations

Semester Exam Deep Learning InternationalEasy

In deep learning, what is the main purpose of Activation functions? Use the application-oriented interpretation.

A. Activation functions are used only in the output layer B. Activation functions introduce nonlinearity into neural networks C. Activation functions store files on disk D. Activation functions always remove gradients

Correct Answer: B. Activation functions introduce nonlinearity into neural networks

Semester Exam Deep Learning InternationalMedium

A student is designing a model and mentions Backpropagation. Which interpretation is most accurate? Use the application-oriented interpretation.

A. Backpropagation requires no loss function B. Backpropagation is only a data augmentation method C. Backpropagation computes gradients by applying the chain rule through the network D. Backpropagation stores images in convolution kernels

Correct Answer: C. Backpropagation computes gradients by applying the chain rule through the network

Semester Exam Deep Learning InternationalMedium

Which option correctly explains Gradient descent in a neural-network workflow? Use the application-oriented interpretation.

A. Gradient descent updates weights randomly without gradients B. Gradient descent is a file compression algorithm C. Gradient descent only applies to databases D. Gradient descent updates parameters in the direction that reduces loss

Correct Answer: D. Gradient descent updates parameters in the direction that reduces loss

Semester Exam Deep Learning InternationalMedium

For an exam question on Learning rate, which answer is most correct? Use the application-oriented interpretation.

A. The learning rate controls the step size of parameter updates B. The learning rate is the number of output classes C. The learning rate is the dataset size D. The learning rate disables optimization

Correct Answer: A. The learning rate controls the step size of parameter updates

Semester Exam Deep Learning InternationalHard

Which misconception about CNN convolution is avoided by the correct answer? Use the application-oriented interpretation.

A. Convolution removes all spatial structure B. Convolution applies learnable filters to local regions of input data C. Convolution always sorts neurons by value D. Convolution is used only for text tokenization

Correct Answer: B. Convolution applies learnable filters to local regions of input data

Semester Exam Deep Learning InternationalHard

When applying deep learning to real-world data, how should CNN pooling be understood? Use the application-oriented interpretation.

A. Pooling is the same as dropout B. Pooling changes class labels C. Pooling reduces spatial dimensions while keeping important features D. Pooling increases image resolution in every layer

Correct Answer: C. Pooling reduces spatial dimensions while keeping important features

Semester Exam Deep Learning InternationalMedium

Which statement would be accepted as correct about CNN feature maps? Use the application-oriented interpretation.

A. A feature map is a confusion matrix B. A feature map is a database table C. A feature map is always a scalar D. A feature map represents filter responses across spatial locations

Correct Answer: D. A feature map represents filter responses across spatial locations

Semester Exam Deep Learning InternationalEasy

Which statement best describes CNN complexity? Use the application-oriented interpretation.

A. CNN computational cost depends on filter size, input size, channels, and number of filters B. CNN complexity is independent of image size C. CNNs have no multiplications D. CNNs require no memory for activations

Correct Answer: A. CNN computational cost depends on filter size, input size, channels, and number of filters

Semester Exam Deep Learning InternationalEasy

In deep learning, what is the main purpose of Autoencoders? Use the application-oriented interpretation.

A. An autoencoder is a SQL trigger B. An autoencoder learns to encode input into a latent representation and reconstruct it C. An autoencoder is always a supervised classifier D. An autoencoder cannot learn compressed features

Correct Answer: B. An autoencoder learns to encode input into a latent representation and reconstruct it

Semester Exam Deep Learning InternationalMedium

A student is designing a model and mentions Sparse coding. Which interpretation is most accurate? Use the application-oriented interpretation.

A. Sparse coding removes the need for input data B. Sparse coding is only a file I/O technique C. Sparse coding encourages representations where only a small number of units are active D. Sparse coding forces every hidden unit to be active

Correct Answer: C. Sparse coding encourages representations where only a small number of units are active

Deep Learning MCQs