Generative Adversarial Network (GAN) Training Task
A Generative Adversarial Network (GAN) Training Task is an unsupervised generative learning task that is a neural network training task (which requires a generator NNet and a discriminator NNet such that the discriminator cannot discriminate between real data and generated data).
- Context:
- It can be solved by a GAN Training System (by implementing a GAN training algorithm).
- …
- Example(s):
- …
- Counter-Example(s):
- an Adversarial ML Algorithm (which assumes the existence of an adversarial opponent to foil its effectiveness).
- Deep Belief Networks.
- See: Backpropagation, Adversarial Learning.