View source for 17953225. METHODS AND SYSTEMS FOR MACHINE LEARNING MODEL TRAINING WITH HUMAN-ASSISTED REFINEMENT simplified abstract (Robert Bosch GmbH)

=METHODS AND SYSTEMS FOR MACHINE LEARNING MODEL TRAINING WITH HUMAN-ASSISTED REFINEMENT=


==Organization Name==

[[:Category:Robert Bosch GmbH|Robert Bosch GmbH]]


[[Category:Robert Bosch GmbH]]

==Inventor(s)==

[[:Category:Wenbin He of Sunnyvale CA (US)|Wenbin He of Sunnyvale CA (US)]][[Category:Wenbin He of Sunnyvale CA (US)]]

[[:Category:Md Naimul Hoque of Fairfax VA (US)|Md Naimul Hoque of Fairfax VA (US)]][[Category:Md Naimul Hoque of Fairfax VA (US)]]

[[:Category:Liang Gou of San Jose CA (US)|Liang Gou of San Jose CA (US)]][[Category:Liang Gou of San Jose CA (US)]]

[[:Category:Liu Ren of Saratoga CA (US)|Liu Ren of Saratoga CA (US)]][[Category:Liu Ren of Saratoga CA (US)]]

==METHODS AND SYSTEMS FOR MACHINE LEARNING MODEL TRAINING WITH HUMAN-ASSISTED REFINEMENT - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17953225 titled 'METHODS AND SYSTEMS FOR MACHINE LEARNING MODEL TRAINING WITH HUMAN-ASSISTED REFINEMENT

==Simplified Explanation==

The abstract describes a method for training a machine learning model using a training dataset of images, where the model identifies images with a specific object type and groups them for user feedback.

* Receiving a training dataset with images
* Identifying images with a specific object type
* Grouping identified images for user feedback
* Generating a user interface for visualization and feedback
* Training the machine learning model based on user feedback

== Potential Applications ==
This technology could be applied in various fields such as image recognition, object detection, and computer vision systems.

== Problems Solved ==
This technology helps in improving the accuracy and efficiency of machine learning models by incorporating user feedback in the training process.

== Benefits ==
The benefits of this technology include enhanced model performance, better object recognition, and increased user engagement through feedback.

== Potential Commercial Applications ==
Potential commercial applications of this technology include image recognition software, automated tagging systems, and visual search engines.

== Possible Prior Art ==
One possible prior art for this technology could be the use of user feedback in training machine learning models in the field of computer vision.

=== What are the specific object types that the model can identify in the images?
The abstract does not specify the specific object types that the model can identify in the images.

=== How does the user feedback impact the training of the machine learning model?
The abstract does not provide details on how exactly the user feedback influences the training of the machine learning model.


==Original Abstract Submitted==

A method for training a machine learning model. The method comprises receiving a training dataset that includes a plurality of images. The method also includes identifying, by a machine learning model, at least one portion of at least one image of the plurality of images in the training dataset associated with a first object type. The method further includes identifying other images having at least one portion that includes the first object type. The method also includes grouping the identified other images into a first image group. The method also includes generating for display a first user interface, that at least includes a rank matrix, wherein a first row of the rank matrix represents the images of the first image object. The user may provide feedback for the visualization using the first interface. The method may also include training the machine learning model based on the user feedback.



[[Category:G06V10/778]]
[[Category:G06N20/00]]
[[Category:G06V10/74]]