Jump to content

Nvidia corporation (20250124640). TRAINING DATA SAMPLING FOR NEURAL NETWORKS

From WikiPatents

TRAINING DATA SAMPLING FOR NEURAL NETWORKS

Organization Name

nvidia corporation

Inventor(s)

Jonathan Peter Lorraine of Toronto CA

Cheng (Kevin) Xie of Toronto CA

Xiaohui Zeng of Toronto CA

Jun Gao of Toronto CA

Sanja Fidler of Toronto CA

James Lucas of Toronto CA

TRAINING DATA SAMPLING FOR NEURAL NETWORKS

This abstract first appeared for US patent application 20250124640 titled 'TRAINING DATA SAMPLING FOR NEURAL NETWORKS

Original Abstract Submitted

apparatuses, systems, and techniques to train one or more neural networks using stratified sampled training data parameters. in at least one embodiment, one or more stochastic training data parameters may be stratified sampled from one or more sampling ranges to compute a gradient for updating the one or more neural networks.

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