17870011. CONTROLLABLE NEURAL NETWORKS OR OTHER CONTROLLABLE MACHINE LEARNING MODELS simplified abstract (Samsung Electronics Co., Ltd.)

From WikiPatents
Jump to navigation Jump to search

CONTROLLABLE NEURAL NETWORKS OR OTHER CONTROLLABLE MACHINE LEARNING MODELS

Organization Name

Samsung Electronics Co., Ltd.

Inventor(s)

Tien Cheng Bau of Irvine CA (US)

CONTROLLABLE NEURAL NETWORKS OR OTHER CONTROLLABLE MACHINE LEARNING MODELS - A simplified explanation of the abstract

This abstract first appeared for US patent application 17870011 titled 'CONTROLLABLE NEURAL NETWORKS OR OTHER CONTROLLABLE MACHINE LEARNING MODELS

Simplified Explanation

The patent application describes a method that involves using a machine learning model to process input data and generate output data based on specified control variables. The method includes providing input data and control variable values to the machine learning model and performing inferencing to generate output data.

  • The method involves using a machine learning model to process input data and generate output data.
  • The machine learning model is trained to process data over a range of values associated with control variables.
  • Input data and control variable values are provided to the machine learning model.
  • Inferencing is performed using the machine learning model to generate output data.
  • The inferencing is controlled based on the specified values of the control variable(s).

Potential Applications

  • This technology can be applied in various fields where machine learning models are used for data processing and generating output.
  • It can be used in industries such as finance, healthcare, manufacturing, and transportation to make predictions or perform analysis based on specified control variables.

Problems Solved

  • The method allows for more precise control over the inferencing process by specifying values for control variables.
  • It enables the machine learning model to generate output data based on specific conditions or requirements.

Benefits

  • The method provides a more flexible and customizable approach to using machine learning models.
  • It allows for targeted analysis and predictions by controlling the values of the control variables.
  • The technology can enhance the accuracy and relevance of the output data generated by the machine learning model.


Original Abstract Submitted

A method includes obtaining (such as accessing, receiving, acquiring, etc.), using at least one processor of an electronic device, a machine learning model trained to process input data and generate output data over at least one range of values associated with one or more control variables. The method also includes providing, using the at least one processor, specified input data to the machine learning model and providing, using the at least one processor, one or more specified values of the one or more control variables to the machine learning model. The one or more specified values of the one or more control variables are within the at least one range of values. The method further includes performing inferencing using the machine learning model to process the specified input data and generate specified output data. The inferencing is controlled based on the one or more specified values of the control variable(s).

Retrieved from "http://wikipatents.org/index.php?title=17870011._CONTROLLABLE_NEURAL_NETWORKS_OR_OTHER_CONTROLLABLE_MACHINE_LEARNING_MODELS_simplified_abstract_(Samsung_Electronics_Co.,_Ltd.)&oldid=20248"