We will explore the use of Generative Adversarial Networks for automatic feature engineering. The idea is to automatically learn a set of features from, potentially noisy, raw data that can be useful in supervised learning tasks such as in computer vision and insurance using synthetic financial transactions data.
sucrerouge / gan_keras Goto Github PK
View Code? Open in Web Editor NEWThis project forked from hamaadshah/gan_tensorflow
Automatic feature engineering using Generative Adversarial Networks.
License: Apache License 2.0