18746171. LEARNING SYSTEM OF MACHINE LEARNING MODEL FOR CLASSIFICATION OF SICKNESS simplified abstract (NEC Corporation)

LEARNING SYSTEM OF MACHINE LEARNING MODEL FOR CLASSIFICATION OF SICKNESS

Organization Name

NEC Corporation

Inventor(s)

Mischa Schmidt of Heidelberg (DE)

Julia Gastinger of Heidelberg (DE)

LEARNING SYSTEM OF MACHINE LEARNING MODEL FOR CLASSIFICATION OF SICKNESS - A simplified explanation of the abstract

This abstract first appeared for US patent application 18746171 titled 'LEARNING SYSTEM OF MACHINE LEARNING MODEL FOR CLASSIFICATION OF SICKNESS

Simplified Explanation:

This patent application describes a method for automated machine learning that involves running multiple automated machine learning frameworks simultaneously on a machine learning task to optimize performance based on available resources and time constraints.

Key Features and Innovation:

• Controlling the execution of multiple automated machine learning frameworks on a machine learning task.
• Training multiple machine learning models and computing performance scores for each model.
• Selecting the best performing machine learning models based on the computed performance scores.

Potential Applications: This technology can be used for:

• Predicting patient discharge in healthcare settings.
• Predictive control in buildings for energy optimization.
• Various other machine learning tasks in different industries.

Problems Solved:

• Efficient utilization of computational resources and time in automated machine learning.
• Improving the performance of machine learning models by selecting the best ones based on performance scores.

Benefits:

• Enhanced accuracy and efficiency in machine learning tasks.
• Time and resource optimization in automated machine learning processes.

Commercial Applications: Potential commercial applications include:

• Healthcare analytics for patient management.
• Energy optimization solutions for smart buildings.
• Customized machine learning solutions for various industries.

Prior Art: Readers can explore prior art related to this technology in the field of automated machine learning frameworks and optimization techniques.

Frequently Updated Research: Stay updated on the latest research in automated machine learning frameworks and performance optimization techniques for machine learning tasks.

Questions about Automated Machine Learning: 1. What are the key advantages of using automated machine learning frameworks in comparison to traditional machine learning approaches? 2. How does the selection of the best performing machine learning models impact the overall efficiency of the machine learning task?

Original Abstract Submitted

A method for automated machine learning includes controlling execution of a plurality of instantiations of different automated machine learning frameworks on a machine learning task each as a separate arm in consideration of available computational resources and time budget. During the execution by the separate arms, a plurality of machine learning models are trained and performance scores of the plurality of trained machine learning models are computed such that one or more of the plurality of trained machine learning models are selectable for the machine learning task based on the performance scores. This invention can be used for predicting patient discharge, predictive control in buildings for energy optimization, and so on.