18244971. HYBRID EXPLAINABLE ARTIFICIAL INTELLIGENCE SYSTEM (BANK OF AMERICA CORPORATION)
HYBRID EXPLAINABLE ARTIFICIAL INTELLIGENCE SYSTEM
Organization Name
Inventor(s)
Emad Noorizadeh of Plano TX (US)
Donatus Asumu of McKinney TX (US)
HYBRID EXPLAINABLE ARTIFICIAL INTELLIGENCE SYSTEM
This abstract first appeared for US patent application 18244971 titled 'HYBRID EXPLAINABLE ARTIFICIAL INTELLIGENCE SYSTEM
Original Abstract Submitted
A hybrid explainable artificial intelligence system may include a shallow learning model and a deep learning model. The shallow learning model may be a machine learning system. The deep learning model may be a neural network. The system may input a data set into both the shallow learning model and the deep learning model. Both the shallow learning model and the deep learning model may produce an output. When there is a common output between the shallow learning model and the deep learning model, the process performed by the shallow learning model may be used to formulate an explanation of the process performed by the deep learning model. The explanation of the process performed by the deep learning model may be used to raise the sensitivity of one or more components of the data set. Such components may include a word or phrase within a transcript.
