Research

Implicit generation and generalization methods for energy-based models

Source: OpenAI News 21 Mar 2019

Listen to Brief

AI audio in English, based on the NadiAI brief and original source.

Brief

We’ve made progress towards stable and scalable training of energy-based models (EBMs) resulting in better sample quality and generalization ability than existing models. Generation in EBMs spends more compute to continually refine its answers and doing so can generate samples competitive with GANs at low temperatures, while also having mode coverage guarantees of likelihood-based models. We hope these findings stimulate further research into this promising class of models.

Why It Matters

Hasil ini boleh menggerakkan lebih banyak kajian terhadap kelas model yang menjanjikan dan memberi alternatif pada GAN serta model likelihood untuk aplikasi generatif.

Keep Reading on NadiAI

Selected Related Articles