GAN（Generative Adversarial Nets）
| العنوان: | GAN（Generative Adversarial Nets） |
|---|---|
| المؤلفون: | Ian Goodfellow, Mehdi Mirza, Sherjil Ozair, Yoshua Bengio, Bing Xu, Jean Pouget-Abadie, David Warde-Farley, Aaron Courville |
| المصدر: | NIPS |
| بيانات النشر: | Japan Society for Fuzzy Theory and Intelligent Informatics, 2017. |
| سنة النشر: | 2017 |
| مصطلحات موضوعية: | Theoretical computer science, Training set, Markov chain, Computer science, business.industry, Adversarial machine learning, Minimax, Machine learning, computer.software_genre, Perceptron, Backpropagation, Approximate inference, Generative model, Discriminative model, Image translation, Artificial intelligence, business, computer |
| الوصف: | 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 ½ 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. |
| تدمد: | 1881-7203 1347-7986 |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_________::3d975d4311ca488f22ba13aae23ad373Test https://doi.org/10.3156/jsoft.29.5_177_2Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.doi...........3d975d4311ca488f22ba13aae23ad373 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 18817203 13477986 |
|---|