A generative adversarial network (GAN) is a type of construct in neural network technology that offers a lot of potential in the world of artificial intelligence. A generative adversarial network is composed of two neural networks: a generative network and a discriminative network. These work together to provide high-level simulation of conceptual tasks.
In a generative adversarial network, the generative network constructs results from input, and “shows” them to the discriminative network. The discriminative network is supposed to distinguish between authentic and synthetic results given by the generative network.
Experts sometimes describe this as the generative network trying to “fool” the discriminative network, which has to be trained to recognize particular sets of patterns and models. The use of generative adversarial networks is somewhat common in image processing, and in the development of new deep stubborn networks that move toward more high-level simulation of human cognitive tasks. Scientists are looking at the potential that generative adversarial networks have to advance the power of neural networks and their ability to “think” in human ways.
0 Comments