Models

The models module implements popular full neural networks. It includes:

• vae.py: A Bernoulli variational autoencoder (Kingma & Welling, 2014)
• wgan_gp.py: A Wasserstein generative adversarial network with gradient penalty (Gulrajani et al., 2017; Goodfellow et al., 2014)
• w2v.py: word2vec model with CBOW and skip-gram architectures and training via noise contrastive estimation (Mikolov et al., 2012)