US 12,614,068 B2 · Systems and methods for training neural networks with sparse data

Abstract

A method, computer readable medium, and system are disclosed for training a neural network model. The method includes the step of selecting an input vector from a set of training data that includes input vectors and sparse target vectors, where each sparse target vector includes target data corresponding to a subset of samples within an output vector of the neural network model. The method also includes the steps of processing the input vector by the neural network model to produce output data for the samples within the output vector and adjusting parameter values of the neural network model to reduce differences between the output vector and the sparse target vector for the subset of the samples.

Claims20

Dependent claims

A processor, comprising:

one or more circuits to:
use one or more neural networks to up-sample one or more input images to produce one or more up-sampled images;
sparsely select one or more pixels of the one or more up-sampled images and one or more pixels of one or more target images;
and
compare values corresponding to the one or more sparsely selected pixels of the one or more up-sampled images to values corresponding to the one or more sparsely selected pixels of the one or more target images to update the one or more neural networks.

2 more elements

Dependencies are inferred from the claim text.

Facts

Application

17/665,370Filed 4 Feb 2022 · continuation

Priority

12 Jun 2017

Published

US 2022/0405582 A122 Dec 2022

Granted

28 Apr 2026

Term ends

Not estimatedThe source records don’t support an estimate.

Classification8 codes

G06N 3/08
Neural networks: learning methods
G06N 3/0464
Architecture, e.g. interconnection topology: convolutional networks [CNN, ConvNet]
G06N 3/0495
Architecture, e.g. interconnection topology: quantised networks; Sparse networks; Compressed networks
G06N 3/063
Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons: using electronic means

Family

Application62/518,435Us provisional application · filed 12 Jun 2017

Application15/881,632Parent of this continuation · filed 26 Jan 2018

US 2022/0405582 A1Pre-grant publication · published 22 Dec 2022

US 11,244,226 B2Parent of this continuation

US 2018/0357537 A1Published application

US 12,614,068 B2This patent

From the US filing history. Foreign family members aren’t listed.

Systems and methods for training neural networks with sparse data

Life of this patent

Systems and methods for training neural networks with sparse data

Life of this patent

Abstract

Claims20