Full Paper Content
1. Introduction
The promise of deep learning is to discover rich, hierarchical models that represent probability distributions over the kinds of data encountered in artificial intelligence applications, such as natural images, audio waveforms containing speech, and symbols in natural language corpora.
2. Related Work
Until recently, most work on deep generative models focused on models that provided a parametric specification of a probability distribution function.
3. Adversarial Nets
The adversarial modeling framework is most straightforward to apply when the models are both multilayer perceptrons. To learn the generator's distribution pg over data x, we define a prior on input noise variables pz(z).
4. Theoretical Results
The generator G implicitly defines a probability distribution pg as the distribution of the samples G(z) obtained when z ∼ pz. Therefore, we would like Algorithm 1 to converge to a good estimator of pdata.
5. Experiments
We trained adversarial nets on a range of datasets including MNIST, the Toronto Face Database (TFD), and CIFAR-10. The generator nets used a mixture of rectifier linear activations and sigmoid activations.