Novel method of training a neural network
AssigneeNVIDIA Corporation
InventorsWonmin Byeon, Shalini De Mello, Ankur Arjun Mali
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and techniques to perform and facilitate preservation of neural coding network weights over time. In at least one embodiment, a convolutional neural coding network is trained using a set of tasks such that said convolutional neural coding network retains an ability to perform inferencing based on tasks from previous training.
Claims31
A processor comprising:
- one or more circuits to use one or more portions of a neural network to infer respectively different information.
A system, comprising memory to store instructions that, as a result of execution by one or more processors, cause the system to:
- use one or more portions of a neural network to infer respectively different information.
A machine-readable medium having stored thereon one or more instructions, which if performed by one or more processors, cause the one or more processors to at least:
- use one or more portions of a neural network to infer respectively different information.
A method comprising:
- using one or more portions of a neural network to infer respectively different information.
Dependencies are inferred from the claim text.