Jump to content

Snap inc. (20250086466). GENERATIVE NEURAL NETWORK DISTILLATION

From WikiPatents

GENERATIVE NEURAL NETWORK DISTILLATION

Organization Name

snap inc.

Inventor(s)

Sergey Tulyakov of Santa Monica CA (US)

Sergei Korolev of Playa Vista CA (US)

Aleksei Stoliar of Los Angeles CA (US)

Maksim Gusarov of Santa Monica CA (US)

Sergei Kotcur of Los Angeles CA (US)

Christopher Yale Crutchfield of San Diego CA (US)

Andrew Wan of Marina del Rey CA (US)

GENERATIVE NEURAL NETWORK DISTILLATION

This abstract first appeared for US patent application 20250086466 titled 'GENERATIVE NEURAL NETWORK DISTILLATION

Original Abstract Submitted

a compact generative neural network can be distilled from a teacher generative neural network using a training network. the compact network can be trained on the input data and output data of the teacher network. the training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.