A Contrastive Learning Approach for Training Variational Autoencoder Priors
Summary of Dai et al.'s NeurIPS 2021 paper introducing Noise Contrastive Priors (NCPs), a novel method using noise contrastive estimation to train …
3 posts tagged with generative-models.
Summary of Dai et al.'s NeurIPS 2021 paper introducing Noise Contrastive Priors (NCPs), a novel method using noise contrastive estimation to train …
VAE tutorial using modern PyTorch: torch.distributions, optimization techniques, numerical stability, and implementation patterns.
Guide to GAN objective functions: Jensen-Shannon, Wasserstein, LSGAN, Fisher distance, and more. Learn which loss function to use when.