View source for 17831738. Modular Machine Learning Architecture simplified abstract (Apple Inc.)

=Modular Machine Learning Architecture=


==Organization Name==

[[:Category:Apple Inc.|Apple Inc.]]


[[Category:Apple Inc.]]

==Inventor(s)==

[[:Category:Shujie Liu of San Jose CA (US)|Shujie Liu of San Jose CA (US)]][[Category:Shujie Liu of San Jose CA (US)]]

[[:Category:Jiefu Zhai of Sunnyvale CA (US)|Jiefu Zhai of Sunnyvale CA (US)]][[Category:Jiefu Zhai of Sunnyvale CA (US)]]

[[:Category:Xiaosong Zhou of Campbell CA (US)|Xiaosong Zhou of Campbell CA (US)]][[Category:Xiaosong Zhou of Campbell CA (US)]]

[[:Category:Hsi-Jung Wu of San Jose CA (US)|Hsi-Jung Wu of San Jose CA (US)]][[Category:Hsi-Jung Wu of San Jose CA (US)]]

[[:Category:Ke Zhang of Mountain View CA (US)|Ke Zhang of Mountain View CA (US)]][[Category:Ke Zhang of Mountain View CA (US)]]

[[:Category:Xiaoxia Sun of Santa Clara CA (US)|Xiaoxia Sun of Santa Clara CA (US)]][[Category:Xiaoxia Sun of Santa Clara CA (US)]]

[[:Category:Jian Li of San Jose CA (US)|Jian Li of San Jose CA (US)]][[Category:Jian Li of San Jose CA (US)]]

==Modular Machine Learning Architecture - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17831738 titled 'Modular Machine Learning Architecture

==Simplified Explanation==

The abstract describes a method where a system uses a machine learning architecture to process input data and generate output data. The architecture consists of three neural networks. The system first generates a feature set from a portion of the input data using the first neural network, and another feature set from another portion of the input data using the second neural network. Finally, the system uses the third neural network to generate output data based on the two feature sets.

* The system accesses input data and a machine learning architecture.
* The machine learning architecture consists of three neural networks.
* The first neural network generates a feature set from a portion of the input data.
* The second neural network generates a feature set from another portion of the input data.
* The third neural network generates output data based on the two feature sets.

== Potential Applications ==
* Data analysis and prediction in various fields such as finance, healthcare, and marketing.
* Image recognition and classification tasks.
* Natural language processing and sentiment analysis.
* Autonomous systems and robotics.

== Problems Solved ==
* Efficiently processing and analyzing large amounts of data.
* Extracting meaningful features from complex input data.
* Improving accuracy and performance of machine learning models.
* Enabling complex tasks that require multiple feature sets.

== Benefits ==
* Improved accuracy and performance in generating output data.
* Enhanced ability to handle complex and diverse input data.
* Increased efficiency in processing and analyzing data.
* Enables the development of more advanced machine learning applications.


==Original Abstract Submitted==

In an example method, a system accesses first input data and a machine learning architecture. The machine learning architecture includes a first module having a first neural network, a second module having a second neural network, and a third module having a third neural network. The system generates a first feature set representing a first portion of the first input data using the first neural network, and a second feature set representing a second portion of the first input data using the second neural network. The system generates, using the third neural network, first output data based on the first feature set and the second feature set.



[[Category:G06N3/045]]