Techniques for classification with neural networks
AssigneeNVIDIA Corporation
InventorsPablo Ribalta, Michal Marcinkiewicz, Dong Yang, Daguang Xu, Przemyslaw Miroslaw Strzelczyk
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and techniques to train neural networks to perform classification. In at least one embodiment, one or more neural networks are trained to perform classification based on, for example, using one or more compressed representations of one or more class labels, where the one or more compressed representations have fewer bits than a representation of the one or more class labels.
Claims30
One or more processors comprising:
- circuitry to train one or more neural networks using one or more binary encodings of one or more classification labels of one or more image segments, wherein the one or more binary encodings comprises fewer bits than the one or more classification labels of the one or more image segments.
A non-transitory machine-readable medium having stored thereon a set of instructions, which if performed by one or more processors, cause the one or more processors to at least:
- train one or more neural networks using one or more binary encodings of one or more classification labels of one or more image segments, wherein the one or more binary encodings comprises fewer bits than the one or more classification labels of the one or more image segments.
A method comprising:
- training one or more neural networks using one or more binary encodings of one or more classification labels of one or more image segments, wherein each of the one or more binary encodings comprises fewer bits than the one or more binary encodings of the one or more classification labels.
A system comprising:
- one or more processors to train one or more neural networks using one or more binary encodings of one or more classification labels of one or more image segments, wherein the one or more binary encodings comprises fewer bits than the one or more classification labels of the one or more image segments;
- and
- one or more memories to store the one or more neural networks.
A medical imaging system comprising:
- one or more processors comprising circuitry to perform image segmentation using one or more neural networks trained, at least in part, by using one or more binary encodings of one or more classification labels of one or more image segments, wherein the one or more binary encodings fewer bits than the one or more classification labels of the one or more image segments;
- and
- one or more memories to store an output of the performed image segmentation.
Dependencies are inferred from the claim text.