Generative adversarial networks
| Autor: | Bing Xu, Aaron Courville, David Warde-Farley, Sherjil Ozair, Ian Goodfellow, Mehdi Mirza, Jean Pouget-Abadie, Yoshua Bengio |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
General Computer Science Computer science business.industry Deep learning Machine Learning (stat.ML) 02 engineering and technology 021001 nanoscience & nanotechnology Machine Learning (cs.LG) Variety (cybernetics) Generative modeling Computer Science - Learning Adversarial system Generative model Statistics - Machine Learning 0202 electrical engineering electronic engineering information engineering Probability distribution 020201 artificial intelligence & image processing Artificial intelligence 0210 nano-technology business Game theory Generative grammar |
| Zdroj: | Communications of the ACM. 63:139-144 |
| ISSN: | 1557-7317 0001-0782 |
| DOI: | 10.1145/3422622 |
| Popis: | We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|