Exam AWS Certified AI Practitioner AIF-C01 topic 1 question 55 discussion

A melhor opção para gerar dados sintéticos baseados em dados existentes seria A. Rede adversária generativa (GAN). As GANs são uma classe de redes neurais que consistem em dois modelos: um gerador e um discriminador. O gerador cria novos exemplos de dados sintéticos, enquanto o discriminador avalia a autenticidade dos dados gerados em comparação com os dados reais. Esse processo iterativo leva a uma melhora na qualidade dos dados sintéticos, tornando-os cada vez mais indistinguíveis dos dados reais.

A. Generative adversarial network (GAN): GANs are specifically designed for generating synthetic data. They consist of two neural networks: a generator and a discriminator. The generator creates synthetic data that resembles the real data, and the discriminator tries to distinguish between real and generated data. This process enables GANs to generate realistic synthetic data, making them ideal for use cases where synthetic data is needed based on existing data.

GANS can do this (A & B can do this task). But, Why can't we use XGBoost to generate the Synthetic data?.

100% A - GANs are specifically designed to generate synthetic data that closely resembles real data. This aligns perfectly with the company's requirement.

Agreed with others, A is correct

should be A

It should be Generative adversarial network (GAN)

Generative Adversarial Network (GAN)

A. Generative adversarial network (GAN) Correct answer. GANs are a type of model specifically designed for generating synthetic data. They consist of two neural networks—a generator and a discriminator—that work together to produce data that mimics the patterns of the original dataset.