View source for 18397909. SYSTEMS AND METHODS FOR AN ACCELERATED AND ENHANCED TUNING OF A MODEL BASED ON PRIOR MODEL TUNING DATA simplified abstract (Intel Corporation)

=SYSTEMS AND METHODS FOR AN ACCELERATED AND ENHANCED TUNING OF A MODEL BASED ON PRIOR MODEL TUNING DATA=


==Organization Name==

[[:Category:Intel Corporation|Intel Corporation]]


[[Category:Intel Corporation]]

==Inventor(s)==

[[:Category:Michael Mccourt of San Francisco CA (US)|Michael Mccourt of San Francisco CA (US)]][[Category:Michael Mccourt of San Francisco CA (US)]]

[[:Category:Ben Hsu of San Francisco CA (US)|Ben Hsu of San Francisco CA (US)]][[Category:Ben Hsu of San Francisco CA (US)]]

[[:Category:Patrick Hayes of San Francisco CA (US)|Patrick Hayes of San Francisco CA (US)]][[Category:Patrick Hayes of San Francisco CA (US)]]

[[:Category:Scott Clark of San Francisco CA (US)|Scott Clark of San Francisco CA (US)]][[Category:Scott Clark of San Francisco CA (US)]]

==SYSTEMS AND METHODS FOR AN ACCELERATED AND ENHANCED TUNING OF A MODEL BASED ON PRIOR MODEL TUNING DATA - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18397909 titled 'SYSTEMS AND METHODS FOR AN ACCELERATED AND ENHANCED TUNING OF A MODEL BASED ON PRIOR MODEL TUNING DATA

==Simplified Explanation==

The patent application abstract describes a method for generating a joint model based on first and second subject models, selecting the joint model after meeting certain criteria, and providing tuning data associated with the joint model to a tuning session of a target model.

* Joint model generated based on first and second subject models
* Selection of joint model from multiple options meeting entropy data point threshold
* Tuning data provided to tuning session of target model

== Potential Applications ==
This technology could be applied in various fields such as machine learning, data analysis, and predictive modeling.

== Problems Solved ==
This technology helps in improving the accuracy and efficiency of models by selecting the best joint model based on specific criteria.

== Benefits ==
The benefits of this technology include enhanced model performance, optimized tuning processes, and improved overall predictive capabilities.

== Potential Commercial Applications ==
One potential commercial application of this technology could be in the development of advanced predictive analytics software for industries such as finance, healthcare, and marketing.

== Possible Prior Art ==
One possible prior art could be the use of ensemble modeling techniques in machine learning to improve model performance and accuracy.

=== Unanswered Questions ===

=== How does this technology compare to existing model selection methods in terms of efficiency and accuracy? ===
This article does not provide a direct comparison to existing model selection methods, leaving the reader to wonder about the specific advantages of this technology over traditional approaches.

=== What are the specific criteria used to determine the threshold for entropy data points in selecting the joint model? ===
The article does not delve into the exact criteria or methodology behind setting the threshold for entropy data points, leaving a gap in understanding the decision-making process behind this aspect of the technology.


==Original Abstract Submitted==

Disclosed examples including generating a joint model based on first and second subject models, the first and second subject models selected based on a relationship between the first and second subject models; selecting the joint model from a plurality of joint models after a determination that entropy data points of the joint model satisfy a threshold, the entropy data points based on multiple tuning trials of the joint model; and providing tuning data associated with the joint model to a tuning session of a target model.



[[Category:G06N20/20]]
[[Category:G06F18/21]]
[[Category:G06F18/211]]
[[Category:G06F18/22]]
[[Category:G06F18/23]]