Learning with multiple stages of representation, typically implemented by a neural network. Depth, connectivity, objective, training experience and parameter sharing are distinct design choices; a deep architecture need not be convolutional or supervised.
A generative adversarial network trains a generator to produce samples and a discriminator to distinguish generated samples from training data. The original objective is the minimax problem
The discriminator improves at detecting fakes; the generator improves at fooling it. Both can be neural networks trained by backpropagation.[ref]
For a toy dataset containing two equally frequent types of images, always producing one type gives the discriminator an exploitable imbalance even if each generated image looks plausible. Under the paper's ideal unrestricted-function analysis, the equilibrium matches the data probability distribution and gives . This ideal result does not ensure convergence for finite networks and alternating numerical updates. Ian Goodfellow and coauthors introduced the framework in 2014.[ref]

Articles by others on the same topic (1)

Deep learning by Ciro Santilli 40 Updated 2025-07-16
Deep learning is the name artificial neural networks basically converged to in the 2010s/2020s.
It is a bit of an unfortunate as it suggests something like "deep understanding" and even reminds one of AGI, which it almost certainly will not attain on its own. But at least it sounds good.