US Patent Application 17824406. Complementary Networks for Rare Event Detection simplified abstract

Complementary Networks for Rare Event Detection

Organization Name

Microsoft Technology Licensing, LLC==Inventor(s)==

[[Category:Xinjian Xue of Carmel IN (US)]]

Complementary Networks for Rare Event Detection - A simplified explanation of the abstract

This abstract first appeared for US patent application 17824406 titled 'Complementary Networks for Rare Event Detection

Simplified Explanation

The patent application describes a computer method for identifying rare events using machine learning networks.

• The method involves receiving information about an event.
• A first machine learning network, trained to classify events in the majority class, is executed on the received information.
• A second machine learning network, trained to classify events in the minority class, is also executed on the received information.
• The first and second machine learning networks can be executed in parallel or sequentially.
• The classifications from both networks are combined to predict the class of the event.

Original Abstract Submitted

A computer implemented method of identifying rare events includes receiving information representative of an event. A first machine learning network trained to classify events in a majority class is executed on the received information representative of the event. A second machine learning network trained to classify events in a minority class is executed on the received information representative of the event. The first and second machine learning networks may be executed in parallel or serially. The classifications of the first and second machine learning networks are then combined to predict the class of the information representative of the event.