Deep Learning Unit 5

What is the primary purpose of an autoencoder?

• Dimensionality reduction

• Image classification

• Speech recognition

• Natural language processing

In an autoencoder, what is the role of the encoder?

• Generate new data samples

• Decode input data

• Extract features and compress input data into a latent space representation

• Apply non-linear transformations to input data

What is the primary goal of a denoising autoencoder?

• Generate noisy images

• Remove noise from input data

• Increase computational complexity

• Enhance feature extraction capabilities

Which of the following statements about autoencoders is true?

• Autoencoders are primarily used for classification tasks.

• Autoencoders always learn a linear transformation of the input data.

• Autoencoders can be trained without any supervision.

• Autoencoders are not suitable for handling high-dimensional data.

What is the primary purpose of Generative Adversarial Networks (GANs)?

• Image classification

• Dimensionality reduction

• Data generation

• Natural language processing

Which component of a GAN is responsible for distinguishing between real and fake samples?

• Discriminator

• Generator

• Critic

• Encoder

In a GAN, what role does the generator network play?

• It discriminates between real and fake samples.

• It generates new samples that mimic the training data.

• It updates the discriminator network.

• It computes the loss function.

What is the training process in a GAN called?

• Supervised learning

• Unsupervised learning

• Reinforcement learning

• Semi-supervised learning

Which of the following techniques is commonly used for reducing the dimensionality of data using autoencoders?

• Principal Component Analysis (PCA)

• Singular Value Decomposition (SVD)

• t-Distributed Stochastic Neighbor Embedding (t-SNE)

• Latent Space Compression (LSC)

Which loss function is commonly used to train the generator network in a GAN?

• Mean Squared Error (MSE)

• Binary Cross-Entropy

• Categorical Cross-Entropy

• Kullback-Leibler Divergence