Unlock instant, AI-driven research and patent intelligence for your innovation.

Privatized machine learning using generative adversarial networks

A machine learning model and machine technology, applied in the field of machine learning, can solve laborious, expensive, time-consuming and other problems

Pending Publication Date: 2019-08-16
APPLE INC
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, current techniques for preparing training datasets can be laborious, time-consuming, and expensive, especially those that involve manually labeling data to generate training datasets

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Privatized machine learning using generative adversarial networks
  • Privatized machine learning using generative adversarial networks
  • Privatized machine learning using generative adversarial networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Various embodiments and aspects will be described herein with reference to details discussed below. The figures will illustrate various embodiments. The following description and drawings are illustrative and should not be construed as limiting. Numerous specific details are described to provide a thorough understanding of various embodiments. However, in certain instances, well-known or conventional details are not described in order to provide a concise discussion of the embodiments.

[0021] Reference in this specification to "one embodiment" or "an embodiment" or "some embodiments" means that a particular feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment. The various appearances of the phrase "an embodiment" in this specification are not necessarily all referring to the same embodiment. It should be noted that there may be changes to the flowcharts or the operations described therein withou...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides privatized machine learning using generative adversarial networks. One embodiment provides for a mobile electronic device comprising a non-transitory machine readable medium tostore instructions. The instructions cause the mobile electronic device to receive a labeled data set from a server and receive a data unit from the server, wherein the data type of the data unit is the same as that of the labeled data set; determine a proposed label for the unit of data via a machine learning model on the mobile electronic device, the machine learning model being used to determine the proposed label for the data unit based on all the labeled data sets from the server and an unlabeled data set associated with the mobile electronic device; encode the proposed label via a privacy algorithm to generate a privatized encoding of the proposed label; and transmit the privatized encoding of the proposed label to the server.

Description

technical field [0001] This disclosure relates generally to the field of machine learning via privatized data. More specifically, the present disclosure relates to a system that implements one or more privacy mechanisms to enable privatized machine learning using generative adversarial networks. Background technique [0002] Machine learning is an application of artificial intelligence that enables complex systems to automatically learn and improve experiences without explicit programming. The accuracy and effectiveness of machine learning models can depend in part on the data used to train those models. For example, a machine learning classifier can be trained using a labeled data set, where the classifier is provided with data samples it learns to recognize along with one or more labels identifying the class of the samples. In general, larger training datasets lead to more accurate classifiers. However, current techniques for preparing training datasets can be laborious...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F21/62G06F21/60
CPCG06F21/6245G06F21/602H04L9/008G06N3/08G06N3/063G06N3/047G06N3/045G06N3/088G06N3/0475G06N3/094H04L67/10G06N20/00
Inventor A·鲍米克A·H·维罗斯R·M·罗杰斯
Owner APPLE INC