Invention Application
- Patent Title: TRAINING GENERATIVE NEURAL NETWORKS THROUGH REINFORCED SELF-TRAINING
-
Application No.: US18358920Application Date: 2023-07-25
-
Publication No.: US20250036958A1Publication Date: 2025-01-30
- Inventor: Caglar Gulcehre , Thomas Le Paine , Srivatsan Srinivasan , Ksenia Konyushkova , Lotte Petronella Jacoba Weerts , Abhishek Sharma , Aditya Siddhant , Orhan Firat
- Applicant: DeepMind Technologies Limited
- Applicant Address: GB London
- Assignee: DeepMind Technologies Limited
- Current Assignee: DeepMind Technologies Limited
- Current Assignee Address: GB London
- Main IPC: G06N3/092
- IPC: G06N3/092 ; G06N3/0475

Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a generative neural network. One of the methods includes training a generative neural network by performing a sequence of a plurality training stages each generating an expanded training data set. The method also involves performing a sequence of improve steps, each comprising training the generative neural network on the training examples in a corresponding subset of the expanded training data set.
Information query