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

Transfer learning and domain adaptation using distributable data models

A technology for distributing models and distributing data, applied in the field of machine learning, and can solve problems such as narrow scope

Inactive Publication Date: 2020-08-18
QOMPLX INC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the data that can be collected through means such as web scraping or news aggregation is relatively narrow in scope compared to crime data stored on devices such as personal mobile devices, or from local police departments

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
  • Transfer learning and domain adaptation using distributable data models
  • Transfer learning and domain adaptation using distributable data models
  • Transfer learning and domain adaptation using distributable data models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present inventors have conceived and put into practice a system and method for exploiting biases contained in distributed data to improve regionalized distributable models.

[0027] One or more different feature aspects may be described in this application. Further, many alternative arrangements may be described for one or more of the feature aspects described herein; it should be understood that these arrangements are presented for purposes of illustration only and are not limiting in any way to the feature aspects contained herein or to the features described herein. Claims presented. One or more arrangements may be applied broadly to many features, as can be readily seen from this disclosure. In general, arrangements are described in sufficient detail to enable a person skilled in the art to practice one or more of the feature aspects, and it is to be understood that other arrangements can be used and can be made without departing from the scope of the particula...

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

A system for transfer learning and domain adaptation using distributable data models is provided, comprising a network-connected distributable model configured to serve instances of a plurality of distributable models; and a directed computation graph module configured to receive at least an instance of at least one of the distributable models from the network -connected computing system, create asecond dataset from machine {earning performed by a transfer engine, train the instance of the distributable model with the second dataset, and generate an update report based at least in part by updates to the instance of the distributable model.

Description

[0001] Cross References Related to Application [0002] This application is a PCT application entitled "TRANSFER LEARNING AND DOMAINADAPTATION USING DISTRIBUTABLE DATA MODELS" filed on December 7, 2017 and claims priority thereto, and is hereby incorporated by reference in its entirety All descriptions thereof are incorporated herein. technical field [0003] The present disclosure relates to the field of machine learning, and more particularly to model improvement using bias contained in data distributed across multiple devices. Background technique [0004] In traditional machine learning, data is usually collected and processed at a central location. The collected data can then be used to train the model. However, the data that can be collected through means such as web scraping or news gathering is relatively narrow in scope compared to crime data stored on a device such as a personal mobile device, or from a local police department. This data can be difficult to leav...

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
IPC IPC(8): G06F16/00G06N20/00
CPCG06N5/022G06N20/00G06N7/01
Inventor 杰森·克拉布特里安德鲁·塞勒斯
Owner QOMPLX INC