Too Long; Didn't Read
Synthetic data generation is one of the new must-have-skills for data scientists. The repository I’ll be covering is a compilation of different generative algorithms to generate synthetic data. The Wasserstein GAN was introduced by Martin Arjovsky in 2017 and promises to improve both the stability when training the model as well as introduces a loss function that is able to correlate with the quality of the generated events. WGAN brings a series of benefits while training these networks: It is less sensitive to model architecture selection (Generator and Critic choice)