In the formulation of Generative Adversarial Networks (GANs), which term represents the objective of the generator to match the distribution of generated samples to that of real data?Question 8Answera.Generator lossb.Adversarial lossc. Reconstruction lossd.Discriminator loss

In a GAN (Generative Adversarial Network), the network is responsible for generating new data, while the network tries to distinguish between real and generated data.

Which of the following best describes the role of the generator in a GAN?To critique imagesTo produce imagesNone of the given optionsTo combine imagesTo evaluate the loss

In Conditional GANs (cGANs), what additional information is provided to both the generator and discriminator during training?Question 20Answera. Image gradientsb.Noise vectorc.Latent space vectorsd.Class labels

What does the discriminator do in a GAN?Creates imagesEnhances image resolutionEvaluates if an image is real or fakeCombines imagesBoth create and evaluate images

So far, I’ve written about three types of generative models, GAN, VAE, and Flow-based models. They have shown great success in generating high-quality samples, but each has some limitations of its own. GAN models are known for potentially unstable training and less diversity in generation due to their adversarial training nature. VAE relies on a surrogate loss. Flow models have to use specialized architectures to construct reversible transform.