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

Exercising artificial intelligence by refining model output

A technology of artificial intelligence and models, applied in computing models, database models, transmission systems, etc.

Pending Publication Date: 2021-01-01
MICROSOFT TECH LICENSING LLC
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Some AI models can be very specific, such as determining whether a weld will break based on X-ray data

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
  • Exercising artificial intelligence by refining model output
  • Exercising artificial intelligence by refining model output
  • Exercising artificial intelligence by refining model output

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] At least some embodiments described herein relate to improved training of artificial intelligence. Raw output data is obtained by applying an input dataset to an artificial intelligence (AI) model. Such raw output data is sometimes difficult to interpret. For example, an AI model tailored for video recognition might recognize a list of objects, relationships, confidence levels, etc. over time. Certain information (eg, the presence of a pen) may not have any association at all. In fact, raw output may contain large amounts of irrelevant or not-so-relevant data. The principles defined in this paper provide a systematic approach to refine the output for various AI models.

[0018] Artificial intelligence (AI) model ensemble representation structures are used for the purpose of refining the AI ​​model output and thus are more useful. For, and perhaps for, each AI model in a large number of AI models, the representation structure represents a refinement of the output dat...

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 improved exercise of artificial intelligence. Raw output data is obtained by applying an input data set to an artificial intelligence (AI). Such raw output data is sometimes difficult to interpret. The principles defined herein provide a systematic way to refine the output for a wide variety of AI models. An AI model collection characterization structure is utilized for purpose of refining AImodel output so as to be more useful. The characterization structure represents, for each of multiple and perhaps numerous AI models, a refinement of output data that resulted from application of an AI model to input data. Upon obtaining output data from the AI model, the appropriate refinement may then be applied. The refined data may then be semantically indexed to provide a semantic index. Thecharacterization structure may also provide tailored information to allow for intuitive querying against the semantic index.

Description

Background technique [0001] Computing systems and associated networks have dramatically changed our world. Computing systems are now capable of participating in various levels of artificial intelligence. Artificial intelligence is the process by which a non-living entity (such as a speech system, speech device, or a combination thereof) receives and interprets data to add structure to at least a portion of the data. [0002] AI can classify the data it receives. As relatively intuitive examples, "image examples" and "video examples" will often be mentioned, where the data input to the AI ​​is images or videos, respectively. In the image example, AI may take raw image data, determine what objects are represented in the image, identify the objects, and possibly determine attributes of those objects. For example, AI can determine the location, orientation, shape, size, etc. of an object. Artificial intelligence can also determine an object's relationship to other objects (suc...

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): G06N5/00G06F16/28G06F16/242G06F16/9035
CPCG06F16/2425G06F16/28G06F16/9035G06N5/025G06N20/20G06F16/901G06F16/904G06F16/90328G06N20/00G06F16/36G10K2210/3024H04L41/16
Inventor V·米塔尔杜亮R·纳拉亚南R·亚伯拉罕
Owner MICROSOFT TECH LICENSING LLC