Regularized Generative Adversarial Network
| Autor: | Gabriele Di Cerbo, Ali Hirsa, Ahmad Shayaan |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: | |
| Popis: | We propose a framework for generating samples from a probability distribution that differs from the probability distribution of the training set. We use an adversarial process that simultaneously trains three networks, a generator and two discriminators. We refer to this new model as regularized generative adversarial network (RegGAN). We evaluate RegGAN on a synthetic dataset composed of gray scale images and we further show that it can be used to learn some pre-specified notions in topology (basic topology properties). The work is motivated by practical problems encountered while using generative methods in the art world. 18 pages. Comments are welcome! |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|