teras.losses module

ctgan_discriminator_loss(y_pred_real, ...)	Loss for the Discriminator model in the CTGAN architecture.
ctgan_generator_loss(x_generated, ...)	Loss for the Generator model in the CTGAN architecture.
saint_constrastive_loss(real, augmented[, ...])	Info-NCE inspired contrastive loss for the pretraining objective in the SAINT architecture proposed in the paper, "SAINT: Improved Neural Networks for Tabular Data".
saint_denoising_loss(real, reconstructed, ...)	Since we apply categorical and numerical embedding layers separately and then combine them into a new features matrix this effectively makes the first k features in the outputs categorical (since categorical embeddings are applied first) and all other features numerical.
tabnet_reconstruction_loss([real, ...])	Reconstruction loss for TabNet Pretrainer mode as proposed by Sercan et al. in the paper, "TabNet: Attentive Interpretable Tabular Learning".