Back to results
US 11,928,764 B2Granted
Neural network motion controller
AssigneeNVIDIA Corporation
InventorsTingwu Wang, Yun Rong Guo, Maria Shugrina, Sanja Fidler
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and techniques to animate objects in computer-generated graphics. In at least one embodiment, one or more neural networks are trained to identify one or more forces to be applied to one or more objects based, at least in part, on training data corresponding to two or more aspects of motion of the one or more objects.
Claims32
A processor comprising:
- one or more circuits to cause two or more disproportionate groups of neural network training data to be proportionally equalized based, at least in part, on one or more accuracy metrics of one or more neural networks to be trained using the training data.
A system, comprising:
- one or more processors to cause two or more disproportionate groups of neural network training data to be proportionally equalized based, at least in part, on one or more accuracy metrics of one or more neural networks to be trained using the training data.
A method, comprising:
- causing two or more disproportionate groups of neural network training data to be proportionally equalized based, at least in part, on one or more accuracy metrics of one or more neural networks to be trained using the training data.
A non-transitory machine-readable medium having stored thereon instructions, which if performed by one or more processors, cause the one or more processors to at least:
- cause two or more disproportionate groups of neural network training data to be proportionally equalized based, at least in part, on one or more accuracy metrics of one or more neural networks to be trained using the training data.
Dependencies are inferred from the claim text.